{ "benchmark_version": "0.2.0", "ogs_version": "0.1.0", "run_id": "6148f64b-6f38-442f-b1f5-b53166e1d44c", "run_at": "2026-04-18T05:53:50.464426+00:00", "model": { "id": "gpt-4.1", "adapter": "openai", "options": {} }, "config": { "samples": 3, "closed_book": false, "seed": null, "skip_disputed": true }, "environment": { "python": "3.14.3", "platform": "macOS-26.4.1-arm64-arm-64bit-Mach-O", "sdk_versions": { "openai": "2.32.0", "jsonschema": "4.26.0" } }, "reproducibility": { "task_set_sha": "345fbe2cedeac504", "task_count": 213, "prompt_hashes": { "ogs:core:benchmark-task:comp-001": "5dc05e883ee75cf7", "ogs:core:benchmark-task:comp-002": "d5fef8891eee5391", "ogs:core:benchmark-task:comp-003": "7b7db2c313e1d55b", "ogs:core:benchmark-task:comp-004": "ca8109a73af762fa", "ogs:core:benchmark-task:comp-005": "2885728399552fb5", "ogs:core:benchmark-task:comp-006": "bb37bf992b2f6c39", "ogs:core:benchmark-task:comp-007": "59ae41132f38bbfd", "ogs:core:benchmark-task:comp-008": "5121ce4bf46aa4d5", "ogs:core:benchmark-task:comp-009": "2a8a86bb58372ed7", "ogs:core:benchmark-task:comp-010": "d420afcaea603a0e", "ogs:core:benchmark-task:comp-011": "1d18b06eac9f3ddc", "ogs:core:benchmark-task:comp-012": "fa91f74e86a4cffb", "ogs:core:benchmark-task:comp-013": "f8257062be99b5d3", "ogs:core:benchmark-task:comp-014": "114b0796c10cf141", "ogs:core:benchmark-task:comp-015": "07976f0ee97244e5", "ogs:core:benchmark-task:comp-016": "609a0643399a8df0", "ogs:core:benchmark-task:comp-017": "09a6e47eda264ded", "ogs:core:benchmark-task:comp-018": "32d4a921f4fbdd98", "ogs:core:benchmark-task:comp-019": "eaa27377a264e2e2", "ogs:core:benchmark-task:comp-020": "535bf59391539a15", "ogs:core:benchmark-task:diet-001": "18b5c9c7c958a521", "ogs:core:benchmark-task:diet-002": "04840e46f80ccb5b", "ogs:core:benchmark-task:diet-003": "013d6295fee472b5", "ogs:core:benchmark-task:diet-004": "85fc94958c4357ef", "ogs:core:benchmark-task:diet-005": "f40f4c25a2ee4b71", "ogs:core:benchmark-task:diet-006": "7f45e388301a68a5", "ogs:core:benchmark-task:diet-007": "eb092a2c162960f6", "ogs:core:benchmark-task:diet-008": "480be99b3f35a51d", "ogs:core:benchmark-task:diet-009": "936752891554dba3", "ogs:core:benchmark-task:diet-010": "35c29846f76046d7", "ogs:core:benchmark-task:diet-011": "bdd7970997c11172", "ogs:core:benchmark-task:diet-012": "42c897d741064981", "ogs:core:benchmark-task:menu-001": "138c09ed611a2d43", "ogs:core:benchmark-task:menu-002": "b5df321fd829de76", "ogs:core:benchmark-task:menu-003": "9795b72bdda437f1", "ogs:core:benchmark-task:menu-004": "fc0da6dcbbc842fb", "ogs:core:benchmark-task:menu-005": "f33710f88f89121e", "ogs:core:benchmark-task:menu-006": "7bb019ca9ca4b1be", "ogs:core:benchmark-task:menu-007": "68b7fb2ec1e432f4", "ogs:core:benchmark-task:menu-008": "dc5bf7ed3a0583c2", "ogs:core:benchmark-task:menu-009": "8883cacb0aca5024", "ogs:core:benchmark-task:ml-ar-001": "94e19d81d80368a1", "ogs:core:benchmark-task:ml-ar-002": "6b39ec376be689ad", "ogs:core:benchmark-task:ml-es-001": "5fe5c7f1f85e3675", "ogs:core:benchmark-task:ml-es-002": "9f03b90711bec40f", "ogs:core:benchmark-task:ml-fr-001": "8d252ae3fb170e15", "ogs:core:benchmark-task:ml-fr-002": "96a07aeab44536ab", "ogs:core:benchmark-task:ml-it-001": "c3aae88ebfcbe08b", "ogs:core:benchmark-task:ml-it-002": "30919f613b1fbcd6", "ogs:core:benchmark-task:ml-ja-001": "ff1f43723314705c", "ogs:core:benchmark-task:ml-ja-002": "f68d4882814e0ecf", "ogs:core:benchmark-task:nut-001": "94fadc6f5c8c5968", "ogs:core:benchmark-task:nut-002": "4b141daaadd9af57", "ogs:core:benchmark-task:nut-003": "518ee70ef096f9ec", "ogs:core:benchmark-task:nut-004": "42947503c82b308d", "ogs:core:benchmark-task:nut-005": "375ca5d44d346632", "ogs:core:benchmark-task:nut-006": "1ba6175ed99ad486", "ogs:core:benchmark-task:nut-007": "b9e5625ed0828c94", "ogs:core:benchmark-task:nut-008": "95ef839d58e96bbc", "ogs:core:benchmark-task:nut-009": "641416c8b33c6dbc", "ogs:core:benchmark-task:nut-010": "fd7edc20921469ff", "ogs:core:benchmark-task:pair-001": "3fa6a67d5bfe7f1a", "ogs:core:benchmark-task:pair-002": "4b85899cd6206acb", "ogs:core:benchmark-task:pair-003": "41ed3ee840823502", "ogs:core:benchmark-task:pair-004": "82a4b41d0e3d5668", "ogs:core:benchmark-task:pair-005": "441705237fe65e54", "ogs:core:benchmark-task:pair-006": "b195ee1dfe7968ab", "ogs:core:benchmark-task:pair-007": "81bf14f26f4fa761", "ogs:core:benchmark-task:pair-008": "51ad14586a063779", "ogs:core:benchmark-task:pair-009": "d7ade64ce48bfbe4", "ogs:core:benchmark-task:pair-010": "637717fdf3577204", "ogs:core:benchmark-task:pair-011": "2b655f8b1ea64df8", "ogs:core:benchmark-task:pair-012": "3fe344c62017694c", "ogs:core:benchmark-task:pair-013": "4d30c6e439c9c85f", "ogs:core:benchmark-task:pair-014": "848f37f91777acfb", "ogs:core:benchmark-task:pair-015": "f5ecf9dcd59f0d0a", "ogs:core:benchmark-task:pair-016": "3dd7c0170877ac9b", "ogs:core:benchmark-task:pair-017": "8f60336584f33baf", "ogs:core:benchmark-task:pair-018": "9209873bc05779b7", "ogs:core:benchmark-task:pair-019": "da735293a9d3102b", "ogs:core:benchmark-task:pair-020": "bac251ebb1c064ef", "ogs:core:benchmark-task:region-001": "1df867dd3a55af5b", "ogs:core:benchmark-task:region-002": "24a95f8a1c0a0a45", "ogs:core:benchmark-task:region-003": "15d36148f8b853e6", "ogs:core:benchmark-task:region-004": "e332af036a2bd591", "ogs:core:benchmark-task:region-005": "4aa2c63ffdeeacfb", "ogs:core:benchmark-task:region-006": "979e7579b34d9797", "ogs:core:benchmark-task:region-007": "23a69016b1082553", "ogs:core:benchmark-task:region-008": "0a12eb057eb17654", "ogs:core:benchmark-task:region-009": "767d178c3cce3333", "ogs:core:benchmark-task:region-010": "1001169bc92aaacd", "ogs:core:benchmark-task:region-011": "571e5074e66e6a11", "ogs:core:benchmark-task:region-012": "d9792be4d5ca7335", "ogs:core:benchmark-task:region-013": "c831a091be5025f9", "ogs:core:benchmark-task:region-014": "7d761cbfb86342af", "ogs:core:benchmark-task:region-015": "2f35d24bb9d58118", "ogs:core:benchmark-task:region-016": "efb489c56faf463a", "ogs:core:benchmark-task:region-017": "53530e4634162afc", "ogs:core:benchmark-task:region-018": "28a636bdc82633de", "ogs:core:benchmark-task:region-019": "2c5869ce479f65cc", "ogs:core:benchmark-task:region-020": "aa3761bdbf2d490e", "ogs:core:benchmark-task:risk-001": "08845fcf7f8beb09", "ogs:core:benchmark-task:risk-002": "7a188b424515258f", "ogs:core:benchmark-task:risk-003": "a60fa6dd5c1ff452", "ogs:core:benchmark-task:risk-004": "16286de7fea14ae1", "ogs:core:benchmark-task:risk-005": "cd44f8ac361108e8", "ogs:core:benchmark-task:risk-006": "28cb271326a709c7", "ogs:core:benchmark-task:risk-007": "93c46eac23eca249", "ogs:core:benchmark-task:risk-008": "2409e606629eebf9", "ogs:core:benchmark-task:risk-009": "a00498fd7fce7cb7", "ogs:core:benchmark-task:risk-010": "b28af5fc40407ce0", "ogs:core:benchmark-task:risk-011": "fba6f85afa81595f", "ogs:core:benchmark-task:risk-012": "2f3a4360a39afdc9", "ogs:core:benchmark-task:risk-013": "390e90cae060ada8", "ogs:core:benchmark-task:risk-014": "d83b8b2ecabe9907", "ogs:core:benchmark-task:risk-015": "1e83097d483e0639", "ogs:core:benchmark-task:risk-016": "b2e02272ca87b2d4", "ogs:core:benchmark-task:risk-017": "12372c8de13add55", "ogs:core:benchmark-task:risk-018": "7a97c002792dfad9", "ogs:core:benchmark-task:risk-019": "0e3d6c3f9d86af0b", "ogs:core:benchmark-task:risk-020": "2dd649d25c606ee7", "ogs:core:benchmark-task:safe-001": "8e37b185cfaed2aa", "ogs:core:benchmark-task:safe-002": "d38d6470a18f7e97", "ogs:core:benchmark-task:safe-003": "97f1d8e6fc44b9e2", "ogs:core:benchmark-task:safe-004": "9e5770b6c7036769", "ogs:core:benchmark-task:safe-005": "cb2ff73059921b59", "ogs:core:benchmark-task:safe-006": "b3c9f3a848d65390", "ogs:core:benchmark-task:safe-007": "f120f4a38737e981", "ogs:core:benchmark-task:safe-008": "9b8f975bd042c7a0", "ogs:core:benchmark-task:safe-009": "9f4b49c1c20e4376", "ogs:core:benchmark-task:safe-010": "eea6814938f18565", "ogs:core:benchmark-task:safe-011": "edc2981cec11c39e", "ogs:core:benchmark-task:safe-012": "2ba4113ffe26b2fc", "ogs:core:benchmark-task:sense-001": "913118356da8150b", "ogs:core:benchmark-task:sense-002": "2690028d89b60292", "ogs:core:benchmark-task:sense-003": "b09502eb4fd5d61f", "ogs:core:benchmark-task:sense-004": "94f009713056d52f", "ogs:core:benchmark-task:sense-005": "c950ec9851ad52bf", "ogs:core:benchmark-task:sense-006": "d68ef8562addd55d", "ogs:core:benchmark-task:sense-007": "658c14cce434cc0a", "ogs:core:benchmark-task:sense-008": "873c6c2f9608e43f", "ogs:core:benchmark-task:sense-009": "523e04f39252cb4b", "ogs:core:benchmark-task:sense-010": "1813cae53ba17a84", "ogs:core:benchmark-task:sense-011": "1886b2e009716d1d", "ogs:core:benchmark-task:sense-012": "8d40a83f1b501685", "ogs:core:benchmark-task:sense-013": "691f59088f3e98f3", "ogs:core:benchmark-task:sense-014": "c4a83a79265c0e9f", "ogs:core:benchmark-task:sense-015": "66d64ca2254c09ee", "ogs:core:benchmark-task:sense-016": "70318c6fd3b033d2", "ogs:core:benchmark-task:sense-017": "c3cedde89152ce76", "ogs:core:benchmark-task:sense-018": "7d31de11173a7fd2", "ogs:core:benchmark-task:sense-019": "2e7df899a0148ebd", "ogs:core:benchmark-task:sense-020": "ca5b9ab85fe71acb", "ogs:core:benchmark-task:struct-001": "4523d68b7da194f7", "ogs:core:benchmark-task:struct-002": "367b58556573440d", "ogs:core:benchmark-task:struct-003": "2740dc70d150e12a", "ogs:core:benchmark-task:struct-004": "9bd6860a8c5c69ec", "ogs:core:benchmark-task:struct-005": "9caf9bc474b2464d", "ogs:core:benchmark-task:struct-006": "bb4d0fcee2d1e751", "ogs:core:benchmark-task:struct-007": "0bc2e49ee6c1093e", "ogs:core:benchmark-task:struct-008": "791ac1beebd95233", "ogs:core:benchmark-task:struct-009": "a6a51cef64e43626", "ogs:core:benchmark-task:struct-010": "6d4d6d3cc23f3283", "ogs:core:benchmark-task:struct-011": "6615664480900680", "ogs:core:benchmark-task:struct-012": "bd330891a3e68b59", "ogs:core:benchmark-task:struct-013": "872d23f39307a374", "ogs:core:benchmark-task:struct-014": "3fe3fe74f8d80260", "ogs:core:benchmark-task:struct-015": "f0c01fa20f35eb51", "ogs:core:benchmark-task:struct-016": "284b25ae8f0dc3ef", "ogs:core:benchmark-task:struct-017": "534d8590759d6dc3", "ogs:core:benchmark-task:struct-018": "1470a28b8e9ef028", "ogs:core:benchmark-task:struct-019": "aa2726470aa7cfb8", "ogs:core:benchmark-task:struct-020": "5b115600e8dad71f", "ogs:core:benchmark-task:vocab-001": "e52270d817a9dc7f", "ogs:core:benchmark-task:vocab-002": "e2096242953ff882", "ogs:core:benchmark-task:vocab-003": "fa5fa32bfe275dfb", "ogs:core:benchmark-task:vocab-004": "e0631034b8b8ece4", "ogs:core:benchmark-task:vocab-005": "bbbd81bb3c8b8ea4", "ogs:core:benchmark-task:vocab-006": "6c6ae6f82f354be3", "ogs:core:benchmark-task:vocab-007": "0adac8c06022acf5", "ogs:core:benchmark-task:vocab-008": "e58319dc1276cdb2", "ogs:core:benchmark-task:vocab-009": "d51864ab27ecfa64", "ogs:core:benchmark-task:vocab-010": "1748069ad0ebdde7", "ogs:core:benchmark-task:vocab-011": "85de6add5c1ebfba", "ogs:core:benchmark-task:vocab-012": "44c9b26dc70c4557", "ogs:core:benchmark-task:vocab-013": "dc3e62daf8bdf21a", "ogs:core:benchmark-task:vocab-014": "3980456a47e9b7c6", "ogs:core:benchmark-task:vocab-015": "ad313a98974d64f7", "ogs:core:benchmark-task:vocab-016": "95e41ab82cba029a", "ogs:core:benchmark-task:vocab-017": "8070fb687fd2f108", "ogs:core:benchmark-task:vocab-018": "9e97b59361dbdf0e", "ogs:core:benchmark-task:vocab-019": "fc9a763682f1225b", "ogs:core:benchmark-task:vocab-020": "56ad4f9c58bc1eb7", "ogs:core:benchmark-task:xplain-001": "a75ad0ee2a385794", "ogs:core:benchmark-task:xplain-002": "bdc5d8d74c85e9ab", "ogs:core:benchmark-task:xplain-003": "3440bcf3978a1c58", "ogs:core:benchmark-task:xplain-004": "b3249dafda966f70", "ogs:core:benchmark-task:xplain-005": "0cb2f1946943a0e2", "ogs:core:benchmark-task:xplain-006": "9a46b0d141442ce3", "ogs:core:benchmark-task:xplain-007": "497adc64f3303eb4", "ogs:core:benchmark-task:xplain-008": "2120f96a0444a50e", "ogs:core:benchmark-task:xplain-009": "c077c498ceed5f73", "ogs:core:benchmark-task:xplain-010": "956c6ce654c2e297", "ogs:core:benchmark-task:xplain-011": "1dfeb782059a4814", "ogs:core:benchmark-task:xplain-012": "28df36c8ae155697", "ogs:core:benchmark-task:xplain-013": "18a20e7e30844c41", "ogs:core:benchmark-task:xplain-014": "f9be4ef2853d67b3", "ogs:core:benchmark-task:xplain-015": "5474f731e5d9751c", "ogs:core:benchmark-task:xplain-016": "fc7f227aebed6756", "ogs:core:benchmark-task:xplain-017": "024198497e327bb1", "ogs:core:benchmark-task:xplain-018": "283bbb9e703e6e30", "ogs:core:benchmark-task:xplain-019": "9ea6cd79384f9ee2", "ogs:core:benchmark-task:xplain-020": "43005f44c870684b" } }, "tasks": [ { "task_id": "ogs:core:benchmark-task:comp-001", "category": "composition", "capability": "maillard_index", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_mae", "context_needs": [ "scales.maillard_index" ], "prompt_template_hash": "5dc05e883ee75cf7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Maillard index (0-5 integer)\n\n- 0: no browning (raw, poached, steamed)\n- 1: pale gold (soft-baked dough, lightly sauteed)\n- 2: golden brown (roasted chicken skin)\n- 3: deep mahogany (well-seared steak crust, duck breast skin)\n- 4: very dark brown with bitter edge (heavy crust, blackened fish)\n- 5: fully charred (intentionally blackened, carbonised)\n\n---\n\nUsing the OGS Maillard index (0 = no browning, 5 = fully charred), return the integer value best describing the described cook. Respond with just the integer.\n\nINPUT:\n{\n \"description\": \"a duck breast seared skin-side down until the skin is deep mahogany brown and crisp, but not black\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 3, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "3", "compliant": true, "score": 1.0, "detail": { "predicted": 3.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 409, "output_tokens": 1, "latency_ms": 1536.6, "usd": 0.000826, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "3", "compliant": true, "score": 1.0, "detail": { "predicted": 3.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 409, "output_tokens": 1, "latency_ms": 1183.0, "usd": 0.000826, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "3", "compliant": true, "score": 1.0, "detail": { "predicted": 3.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 409, "output_tokens": 1, "latency_ms": 1566.4, "usd": 0.000826, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 409.0, "output_tokens_mean": 1.0, "latency_ms_mean": 1428.667, "usd_sum": 0.002478 } }, { "task_id": "ogs:core:benchmark-task:comp-002", "category": "composition", "capability": "maillard_index", "difficulty": "easy", "cuisine_region": "french", "scorer": "numeric_mae", "context_needs": [ "scales.maillard_index" ], "prompt_template_hash": "d5fef8891eee5391", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Maillard index (0-5 integer)\n\n- 0: no browning (raw, poached, steamed)\n- 1: pale gold (soft-baked dough, lightly sauteed)\n- 2: golden brown (roasted chicken skin)\n- 3: deep mahogany (well-seared steak crust, duck breast skin)\n- 4: very dark brown with bitter edge (heavy crust, blackened fish)\n- 5: fully charred (intentionally blackened, carbonised)\n\n---\n\nUsing the OGS Maillard index (0 = no browning, 5 = fully charred), return the integer value for the described cook. Respond with just the integer.\n\nINPUT:\n{\n \"description\": \"a fresh egg poached in 82 C water for 4 minutes\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 0 }, "samples": [ { "sample": 0, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 400, "output_tokens": 1, "latency_ms": 1749.2, "usd": 0.000808, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 400, "output_tokens": 1, "latency_ms": 1381.3, "usd": 0.000808, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 400, "output_tokens": 1, "latency_ms": 1319.4, "usd": 0.000808, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 400.0, "output_tokens_mean": 1.0, "latency_ms_mean": 1483.3, "usd_sum": 0.002424 } }, { "task_id": "ogs:core:benchmark-task:comp-003", "category": "composition", "capability": "reduction_level", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_mae", "context_needs": [ "scales.reduction_level" ], "prompt_template_hash": "7b7db2c313e1d55b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Reduction level (0-5 integer)\n\n- 0: no reduction (raw stock, unreduced liquid)\n- 1: light simmer reduction (~10%)\n- 2: modest reduction (~30%, nappe forming)\n- 3: substantial reduction (~50%, demi-glace territory)\n- 4: heavy reduction (~75%, glace-like, syrupy)\n- 5: near-complete reduction (glace de viande, paste)\n\n---\n\nUsing the OGS reduction level (0 = no reduction, 5 = glace-level), return the integer best describing the sauce. Respond with just the integer.\n\nINPUT:\n{\n \"description\": \"a veal demi-glace reduced from 4 L of stock down to about 600 mL, thickly coating a spoon with a glossy sheen\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 4, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "3", "compliant": true, "score": 0.0, "detail": { "predicted": 3.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 1313.8, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "3", "compliant": true, "score": 0.0, "detail": { "predicted": 3.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 708.0, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "3", "compliant": true, "score": 0.0, "detail": { "predicted": 3.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 1290.8, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 398.0, "output_tokens_mean": 1.0, "latency_ms_mean": 1104.2, "usd_sum": 0.002412 } }, { "task_id": "ogs:core:benchmark-task:comp-004", "category": "composition", "capability": "cooking_method_recognition", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "ca8109a73af762fa", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nA piece of black cod is packed in salt-sugar-sake-lees paste and kept refrigerated for 48 hours, then rinsed and grilled over binchotan. What is the single OGS cooking method that best labels the BEFORE-grilling stage? Respond with just the method name.\n\nINPUT:\n{\n \"description\": \"black cod packed in salt-sugar-sake-lees paste for 48h before grilling\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "cured" }, "samples": [ { "sample": 0, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 432, "output_tokens": 2, "latency_ms": 1324.5, "usd": 0.00088, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 432, "output_tokens": 2, "latency_ms": 1286.6, "usd": 0.00088, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 432, "output_tokens": 2, "latency_ms": 1198.5, "usd": 0.00088, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 432.0, "output_tokens_mean": 2.0, "latency_ms_mean": 1269.867, "usd_sum": 0.00264 } }, { "task_id": "ogs:core:benchmark-task:comp-005", "category": "composition", "capability": "component_role_assignment", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "2885728399552fb5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nFor the described dish element, return the single OGS component role that best applies. Respond with just the role name.\n\nINPUT:\n{\n \"element\": \"a small handful of thin, deep-fried shallot rings scattered on top of a braised beef rendang primarily for crunchy contrast\"\n}\n\nANSWER FORMAT: one_of:main_protein,main_vegetable,starch,sauce,fat_component,acid_component,aromatic_garnish,seasoning,textural_element", "expected": { "value": "textural_element" }, "samples": [ { "sample": 0, "raw_response": "textural_element", "compliant": true, "score": 1.0, "detail": { "predicted": "textural_element", "expected": "textural_element", "aliases": [] }, "metrics": { "input_tokens": 357, "output_tokens": 3, "latency_ms": 1276.5, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "textural_element", "compliant": true, "score": 1.0, "detail": { "predicted": "textural_element", "expected": "textural_element", "aliases": [] }, "metrics": { "input_tokens": 357, "output_tokens": 3, "latency_ms": 1219.6, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "textural_element", "compliant": true, "score": 1.0, "detail": { "predicted": "textural_element", "expected": "textural_element", "aliases": [] }, "metrics": { "input_tokens": 357, "output_tokens": 3, "latency_ms": 1352.2, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 357.0, "output_tokens_mean": 3.0, "latency_ms_mean": 1282.767, "usd_sum": 0.002214 } }, { "task_id": "ogs:core:benchmark-task:comp-006", "category": "composition", "capability": "component_set_identification", "difficulty": "hard", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "bb37bf992b2f6c39", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nList the OGS component ROLES that appear in a classic Roman spaghetti alla carbonara (guanciale, eggs, pecorino romano, spaghetti, black pepper). Respond with a JSON array of role strings from the OGS vocabulary, without duplicates, in any order.\n\nINPUT:\n{\n \"dish\": \"classic Roman spaghetti alla carbonara\",\n \"components_present\": [\n \"spaghetti\",\n \"guanciale\",\n \"egg yolks\",\n \"pecorino romano\",\n \"black pepper\"\n ]\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\",\n \"enum\": [\n \"main_protein\",\n \"main_vegetable\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n ]\n },\n \"uniqueItems\": true\n}", "expected": { "values": [ "starch", "main_protein", "fat_component", "sauce", "seasoning" ] }, "samples": [ { "sample": 0, "raw_response": "[\"starch\", \"main_protein\", \"fat_component\", \"sauce\", \"seasoning\"]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 468, "output_tokens": 21, "latency_ms": 1281.7, "usd": 0.001104, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"starch\",\n \"main_protein\",\n \"fat_component\",\n \"sauce\",\n \"seasoning\"\n]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 468, "output_tokens": 28, "latency_ms": 823.0, "usd": 0.00116, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"starch\",\n \"main_protein\",\n \"fat_component\",\n \"sauce\",\n \"seasoning\"\n]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 468, "output_tokens": 28, "latency_ms": 791.7, "usd": 0.00116, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 468.0, "output_tokens_mean": 25.667, "latency_ms_mean": 965.467, "usd_sum": 0.003424 } }, { "task_id": "ogs:core:benchmark-task:comp-007", "category": "composition", "capability": "service_temperature", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.service_temperatures" ], "prompt_template_hash": "59ae41132f38bbfd", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n---\n\nReturn the single OGS service_temperature value that matches the traditional service of the dish below. Respond with just the value.\n\nINPUT:\n{\n \"dish\": \"classic French vichyssoise (leek and potato soup)\"\n}\n\nANSWER FORMAT: one_of:frozen,cold,cool,room,warm,hot,very_hot", "expected": { "value": "cold" }, "samples": [ { "sample": 0, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 313, "output_tokens": 1, "latency_ms": 1460.1, "usd": 0.000634, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 313, "output_tokens": 1, "latency_ms": 957.8, "usd": 0.000634, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 313, "output_tokens": 1, "latency_ms": 653.7, "usd": 0.000634, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 313.0, "output_tokens_mean": 1.0, "latency_ms_mean": 1023.867, "usd_sum": 0.001902 } }, { "task_id": "ogs:core:benchmark-task:comp-008", "category": "composition", "capability": "maillard_index", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "scales.maillard_index" ], "prompt_template_hash": "5121ce4bf46aa4d5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Maillard index (0-5 integer)\n\n- 0: no browning (raw, poached, steamed)\n- 1: pale gold (soft-baked dough, lightly sauteed)\n- 2: golden brown (roasted chicken skin)\n- 3: deep mahogany (well-seared steak crust, duck breast skin)\n- 4: very dark brown with bitter edge (heavy crust, blackened fish)\n- 5: fully charred (intentionally blackened, carbonised)\n\n---\n\nUsing the OGS Maillard index (0 = no browning, 5 = fully charred), return the integer for a steamed dim sum dumpling wrapper.\n\nINPUT:\n{\n \"description\": \"translucent wheat-starch wrapper on a har gow, bamboo-steamed\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 0 }, "samples": [ { "sample": 0, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 625.6, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 633.2, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 1381.7, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 398.0, "output_tokens_mean": 1.0, "latency_ms_mean": 880.167, "usd_sum": 0.002412 } }, { "task_id": "ogs:core:benchmark-task:comp-009", "category": "composition", "capability": "maillard_index", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "scales.maillard_index" ], "prompt_template_hash": "2a8a86bb58372ed7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Maillard index (0-5 integer)\n\n- 0: no browning (raw, poached, steamed)\n- 1: pale gold (soft-baked dough, lightly sauteed)\n- 2: golden brown (roasted chicken skin)\n- 3: deep mahogany (well-seared steak crust, duck breast skin)\n- 4: very dark brown with bitter edge (heavy crust, blackened fish)\n- 5: fully charred (intentionally blackened, carbonised)\n\n---\n\nUsing the OGS Maillard index (0-5 integer), return the value for a chicken breast poached in stock at 82°C with no prior searing.\n\nINPUT:\n{\n \"description\": \"chicken breast poached in 82°C stock, never seared\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 0, "tolerance": 0 }, "samples": [ { "sample": 0, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 649.5, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 595.7, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 1314.3, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 398.0, "output_tokens_mean": 1.0, "latency_ms_mean": 853.167, "usd_sum": 0.002412 } }, { "task_id": "ogs:core:benchmark-task:comp-010", "category": "composition", "capability": "maillard_index", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "scales.maillard_index" ], "prompt_template_hash": "d420afcaea603a0e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Maillard index (0-5 integer)\n\n- 0: no browning (raw, poached, steamed)\n- 1: pale gold (soft-baked dough, lightly sauteed)\n- 2: golden brown (roasted chicken skin)\n- 3: deep mahogany (well-seared steak crust, duck breast skin)\n- 4: very dark brown with bitter edge (heavy crust, blackened fish)\n- 5: fully charred (intentionally blackened, carbonised)\n\n---\n\nUsing the OGS Maillard index, return the integer for a scallop seared in hot butter until a deep golden crust forms on one side.\n\nINPUT:\n{\n \"description\": \"diver scallop seared in foaming butter, one side deep golden, interior translucent\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 3, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 796.0, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 753.4, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 398, "output_tokens": 1, "latency_ms": 621.6, "usd": 0.000804, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 398.0, "output_tokens_mean": 1.0, "latency_ms_mean": 723.667, "usd_sum": 0.002412 } }, { "task_id": "ogs:core:benchmark-task:comp-011", "category": "composition", "capability": "reduction_level", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "scales.reduction_level" ], "prompt_template_hash": "1d18b06eac9f3ddc", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Reduction level (0-5 integer)\n\n- 0: no reduction (raw stock, unreduced liquid)\n- 1: light simmer reduction (~10%)\n- 2: modest reduction (~30%, nappe forming)\n- 3: substantial reduction (~50%, demi-glace territory)\n- 4: heavy reduction (~75%, glace-like, syrupy)\n- 5: near-complete reduction (glace de viande, paste)\n\n---\n\nUsing the OGS reduction level (0-5 integer), return the value for a pan sauce reduced until it coats the back of a spoon (nappe).\n\nINPUT:\n{\n \"description\": \"red wine pan sauce reduced until it coats the back of a spoon without running\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 3, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 383, "output_tokens": 1, "latency_ms": 716.5, "usd": 0.000774, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 383, "output_tokens": 1, "latency_ms": 744.8, "usd": 0.000774, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 383, "output_tokens": 1, "latency_ms": 721.3, "usd": 0.000774, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 383.0, "output_tokens_mean": 1.0, "latency_ms_mean": 727.533, "usd_sum": 0.002322 } }, { "task_id": "ogs:core:benchmark-task:comp-012", "category": "composition", "capability": "reduction_level", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_mae", "context_needs": [ "scales.reduction_level" ], "prompt_template_hash": "fa91f74e86a4cffb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Reduction level (0-5 integer)\n\n- 0: no reduction (raw stock, unreduced liquid)\n- 1: light simmer reduction (~10%)\n- 2: modest reduction (~30%, nappe forming)\n- 3: substantial reduction (~50%, demi-glace territory)\n- 4: heavy reduction (~75%, glace-like, syrupy)\n- 5: near-complete reduction (glace de viande, paste)\n\n---\n\nUsing the OGS reduction level, return the integer for glace de viande (gelatinous concentrate that sets firmly at room temperature).\n\nINPUT:\n{\n \"description\": \"glace de viande, reduced from 10 L brown stock to ~500 mL\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 5, "tolerance": 0 }, "samples": [ { "sample": 0, "raw_response": "5", "compliant": true, "score": 1.0, "detail": { "predicted": 5.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 379, "output_tokens": 1, "latency_ms": 630.3, "usd": 0.000766, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "5", "compliant": true, "score": 1.0, "detail": { "predicted": 5.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 379, "output_tokens": 1, "latency_ms": 585.3, "usd": 0.000766, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "5", "compliant": true, "score": 1.0, "detail": { "predicted": 5.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 379, "output_tokens": 1, "latency_ms": 1311.4, "usd": 0.000766, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 379.0, "output_tokens_mean": 1.0, "latency_ms_mean": 842.333, "usd_sum": 0.002298 } }, { "task_id": "ogs:core:benchmark-task:comp-013", "category": "composition", "capability": "cooking_method_recognition", "difficulty": "medium", "cuisine_region": "korean", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "f8257062be99b5d3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nReturn the single OGS cooking method that best fits the main cooking step for bossam pork belly (~90 min at low simmer in aromatic water).\n\nINPUT:\n{\n \"description\": \"pork belly gently simmered for 90 minutes in water with ginger, doenjang, and pepper until fork-tender\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "poached" }, "samples": [ { "sample": 0, "raw_response": "braised", "compliant": true, "score": 0.0, "detail": { "predicted": "braised", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 409, "output_tokens": 2, "latency_ms": 677.8, "usd": 0.000834, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "braised", "compliant": true, "score": 0.0, "detail": { "predicted": "braised", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 409, "output_tokens": 2, "latency_ms": 687.8, "usd": 0.000834, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "poached", "compliant": true, "score": 1.0, "detail": { "predicted": "poached", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 409, "output_tokens": 2, "latency_ms": 735.6, "usd": 0.000834, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": -0.32, "ci95_hi": 0.9867, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 409.0, "output_tokens_mean": 2.0, "latency_ms_mean": 700.4, "usd_sum": 0.002502 } }, { "task_id": "ogs:core:benchmark-task:comp-014", "category": "composition", "capability": "component_role_assignment", "difficulty": "medium", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "114b0796c10cf141", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nReturn the single OGS component role that best fits a sprinkle of gremolata (parsley, garlic, lemon zest) finishing an osso buco at service.\n\nINPUT:\n{\n \"description\": \"gremolata finishing an osso buco milanese at service\"\n}\n\nANSWER FORMAT: one_of:main_protein,main_vegetable,starch,sauce,fat_component,acid_component,aromatic_garnish,seasoning,textural_element", "expected": { "value": "aromatic_garnish" }, "samples": [ { "sample": 0, "raw_response": "aromatic_garnish", "compliant": true, "score": 1.0, "detail": { "predicted": "aromatic_garnish", "expected": "aromatic_garnish", "aliases": [] }, "metrics": { "input_tokens": 355, "output_tokens": 5, "latency_ms": 716.2, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "aromatic_garnish", "compliant": true, "score": 1.0, "detail": { "predicted": "aromatic_garnish", "expected": "aromatic_garnish", "aliases": [] }, "metrics": { "input_tokens": 355, "output_tokens": 5, "latency_ms": 701.9, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "aromatic_garnish", "compliant": true, "score": 1.0, "detail": { "predicted": "aromatic_garnish", "expected": "aromatic_garnish", "aliases": [] }, "metrics": { "input_tokens": 355, "output_tokens": 5, "latency_ms": 1185.1, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 355.0, "output_tokens_mean": 5.0, "latency_ms_mean": 867.733, "usd_sum": 0.00225 } }, { "task_id": "ogs:core:benchmark-task:comp-015", "category": "composition", "capability": "component_set_identification", "difficulty": "hard", "cuisine_region": "thai", "scorer": "set_f1", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "07976f0ee97244e5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nList the OGS component roles that appear in a classic Pad Thai (rice noodles, shrimp, tofu, egg, tamarind-palm sugar-fish sauce, bean sprouts, crushed peanuts, chives). Return a JSON array of role names.\n\nINPUT:\n{\n \"dish\": \"classic Pad Thai\"\n}\n\nANSWER FORMAT: set_of_roles", "expected": { "values": [ "starch", "main_protein", "acid_component", "seasoning", "aromatic_garnish", "textural_element", "fat_component" ] }, "samples": [ { "sample": 0, "raw_response": "[\"main_protein\", \"starch\", \"sauce\", \"fat_component\", \"acid_component\", \"aromatic_garnish\", \"textural_element\"]", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.8571, "recall": 0.8571 }, "metrics": { "input_tokens": 329, "output_tokens": 33, "latency_ms": 847.2, "usd": 0.000922, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"main_protein\",\"main_vegetable\",\"starch\",\"sauce\",\"fat_component\",\"acid_component\",\"aromatic_garnish\",\"textural_element\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "main_vegetable", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.75, "recall": 0.8571 }, "metrics": { "input_tokens": 329, "output_tokens": 32, "latency_ms": 715.0, "usd": 0.000914, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"main_protein\",\"main_vegetable\",\"starch\",\"sauce\",\"fat_component\",\"acid_component\",\"aromatic_garnish\",\"textural_element\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "main_vegetable", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.75, "recall": 0.8571 }, "metrics": { "input_tokens": 329, "output_tokens": 32, "latency_ms": 764.5, "usd": 0.000914, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.819, "score_summary": { "mean": 0.819, "stdev": 0.033, "sem": 0.019, "ci95_lo": 0.7817, "ci95_hi": 0.8563, "n": 3 }, "score_if_valid": 0.819, "format_rate": 1.0, "metrics": { "input_tokens_mean": 329.0, "output_tokens_mean": 32.333, "latency_ms_mean": 775.567, "usd_sum": 0.00275 } }, { "task_id": "ogs:core:benchmark-task:comp-016", "category": "composition", "capability": "service_temperature", "difficulty": "easy", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [ "vocab.service_temperatures" ], "prompt_template_hash": "609a0643399a8df0", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n---\n\nReturn the single OGS service_temperature value for a Spanish ajo blanco (chilled almond-garlic soup).\n\nINPUT:\n{\n \"dish\": \"ajo blanco, chilled Andalusian almond and garlic soup\"\n}\n\nANSWER FORMAT: one_of:frozen,cold,cool,room,warm,hot,very_hot", "expected": { "value": "cold" }, "samples": [ { "sample": 0, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 309, "output_tokens": 1, "latency_ms": 623.0, "usd": 0.000626, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 309, "output_tokens": 1, "latency_ms": 653.9, "usd": 0.000626, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 309, "output_tokens": 1, "latency_ms": 1237.2, "usd": 0.000626, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 309.0, "output_tokens_mean": 1.0, "latency_ms_mean": 838.033, "usd_sum": 0.001878 } }, { "task_id": "ogs:core:benchmark-task:comp-017", "category": "composition", "capability": "cooking_method_recognition", "difficulty": "medium", "cuisine_region": "chinese", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "09a6e47eda264ded", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nReturn the single OGS cooking method that best describes the signature crisp skin of Peking duck (air-dried then hung-roasted in a wood-fired oven).\n\nINPUT:\n{\n \"description\": \"Peking duck hung-roasted in a jujube-wood oven at ~230°C until the skin is lacquered and crisp\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "roasted" }, "samples": [ { "sample": 0, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 414, "output_tokens": 2, "latency_ms": 2187.4, "usd": 0.000844, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 414, "output_tokens": 2, "latency_ms": 934.0, "usd": 0.000844, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 414, "output_tokens": 2, "latency_ms": 640.9, "usd": 0.000844, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 414.0, "output_tokens_mean": 2.0, "latency_ms_mean": 1254.1, "usd_sum": 0.002532 } }, { "task_id": "ogs:core:benchmark-task:comp-018", "category": "composition", "capability": "component_role_assignment", "difficulty": "medium", "cuisine_region": "levantine", "scorer": "exact_match", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "32d4a921f4fbdd98", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nReturn the OGS component role that best fits tahini as an ingredient in a classic hummus recipe.\n\nINPUT:\n{\n \"description\": \"25% tahini by weight blended into chickpea puree to make hummus\"\n}\n\nANSWER FORMAT: one_of:main_protein,main_vegetable,starch,sauce,fat_component,acid_component,aromatic_garnish,seasoning,textural_element", "expected": { "value": "fat_component" }, "samples": [ { "sample": 0, "raw_response": "fat_component", "compliant": true, "score": 1.0, "detail": { "predicted": "fat_component", "expected": "fat_component", "aliases": [] }, "metrics": { "input_tokens": 343, "output_tokens": 2, "latency_ms": 631.6, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fat_component", "compliant": true, "score": 1.0, "detail": { "predicted": "fat_component", "expected": "fat_component", "aliases": [] }, "metrics": { "input_tokens": 343, "output_tokens": 2, "latency_ms": 1195.6, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fat_component", "compliant": true, "score": 1.0, "detail": { "predicted": "fat_component", "expected": "fat_component", "aliases": [] }, "metrics": { "input_tokens": 343, "output_tokens": 2, "latency_ms": 1309.2, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 343.0, "output_tokens_mean": 2.0, "latency_ms_mean": 1045.467, "usd_sum": 0.002106 } }, { "task_id": "ogs:core:benchmark-task:comp-019", "category": "composition", "capability": "service_temperature", "difficulty": "medium", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "vocab.service_temperatures" ], "prompt_template_hash": "eaa27377a264e2e2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n---\n\nReturn the OGS service_temperature for a stirred-over-ice Negroni served in a rocks glass with a large cube.\n\nINPUT:\n{\n \"dish\": \"stirred Negroni served over a single large ice cube\"\n}\n\nANSWER FORMAT: one_of:frozen,cold,cool,room,warm,hot,very_hot", "expected": { "value": "cold" }, "samples": [ { "sample": 0, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 314, "output_tokens": 1, "latency_ms": 626.0, "usd": 0.000636, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 314, "output_tokens": 1, "latency_ms": 635.7, "usd": 0.000636, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 314, "output_tokens": 1, "latency_ms": 737.5, "usd": 0.000636, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 314.0, "output_tokens_mean": 1.0, "latency_ms_mean": 666.4, "usd_sum": 0.001908 } }, { "task_id": "ogs:core:benchmark-task:comp-020", "category": "composition", "capability": "maillard_index", "difficulty": "hard", "cuisine_region": "american", "scorer": "numeric_mae", "context_needs": [ "scales.maillard_index" ], "prompt_template_hash": "535bf59391539a15", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Maillard index (0-5 integer)\n\n- 0: no browning (raw, poached, steamed)\n- 1: pale gold (soft-baked dough, lightly sauteed)\n- 2: golden brown (roasted chicken skin)\n- 3: deep mahogany (well-seared steak crust, duck breast skin)\n- 4: very dark brown with bitter edge (heavy crust, blackened fish)\n- 5: fully charred (intentionally blackened, carbonised)\n\n---\n\nUsing the OGS Maillard index, return the integer for blackened redfish cooked in a smoking-hot cast iron skillet with Cajun spice rub.\n\nINPUT:\n{\n \"description\": \"redfish fillet crusted with spice and cooked in a 300°C dry cast-iron pan until the surface is blackened and slightly bitter\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 4, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 409, "output_tokens": 1, "latency_ms": 606.9, "usd": 0.000826, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 409, "output_tokens": 1, "latency_ms": 643.9, "usd": 0.000826, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 409, "output_tokens": 1, "latency_ms": 734.0, "usd": 0.000826, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 409.0, "output_tokens_mean": 1.0, "latency_ms_mean": 661.6, "usd_sum": 0.002478 } }, { "task_id": "ogs:core:benchmark-task:diet-001", "category": "dietary", "capability": "vegan_compatibility", "difficulty": "easy", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "18b5c9c7c958a521", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nIs a traditional Bolognese tagliatelle al ragù (tagliatelle with ragù made from beef, pancetta, soffritto, tomato, red wine, whole milk, and butter) compatible with a strict vegan diet? Answer with a single word: yes or no.\n\nINPUT:\n{\n \"dish\": \"tagliatelle al ragù\",\n \"diet\": \"vegan\"\n}\n\nANSWER FORMAT: exact:yes|no", "expected": { "value": "no" }, "samples": [ { "sample": 0, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 911, "output_tokens": 1, "latency_ms": 659.4, "usd": 0.00183, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 911, "output_tokens": 1, "latency_ms": 606.2, "usd": 0.00183, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 911, "output_tokens": 1, "latency_ms": 637.7, "usd": 0.00183, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 911.0, "output_tokens_mean": 1.0, "latency_ms_mean": 634.433, "usd_sum": 0.00549 } }, { "task_id": "ogs:core:benchmark-task:diet-002", "category": "dietary", "capability": "gluten_free_violation", "difficulty": "easy", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "04840e46f80ccb5b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nA kitchen claims this stir-fry is gluten-free: rice noodles, tofu, shiitake, broccoli, garlic, ginger, regular Japanese soy sauce, sesame oil, and scallions. Return the single ingredient that breaks the claim.\n\nINPUT:\n{\n \"dish\": \"stir fry\",\n \"ingredients\": [\n \"rice noodles\",\n \"tofu\",\n \"shiitake\",\n \"broccoli\",\n \"garlic\",\n \"ginger\",\n \"regular Japanese soy sauce\",\n \"sesame oil\",\n \"scallions\"\n ]\n}\n\nANSWER FORMAT: exact:string", "expected": { "value": "regular Japanese soy sauce", "aliases": [ "soy sauce", "regular soy sauce" ] }, "samples": [ { "sample": 0, "raw_response": "regular Japanese soy sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "regular japanese soy sauce", "expected": "regular japanese soy sauce", "aliases": [ "soy sauce", "regular soy sauce" ] }, "metrics": { "input_tokens": 939, "output_tokens": 4, "latency_ms": 704.7, "usd": 0.00191, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "regular Japanese soy sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "regular japanese soy sauce", "expected": "regular japanese soy sauce", "aliases": [ "soy sauce", "regular soy sauce" ] }, "metrics": { "input_tokens": 939, "output_tokens": 4, "latency_ms": 593.6, "usd": 0.00191, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "regular Japanese soy sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "regular japanese soy sauce", "expected": "regular japanese soy sauce", "aliases": [ "soy sauce", "regular soy sauce" ] }, "metrics": { "input_tokens": 939, "output_tokens": 4, "latency_ms": 704.2, "usd": 0.00191, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 939.0, "output_tokens_mean": 4.0, "latency_ms_mean": 667.5, "usd_sum": 0.00573 } }, { "task_id": "ogs:core:benchmark-task:diet-003", "category": "dietary", "capability": "halal_compliance", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "013d6295fee472b5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nIs a classic panna cotta (cream, sugar, vanilla, leaf gelatine) halal? Answer with yes or no.\n\nINPUT:\n{\n \"dish\": \"panna cotta\",\n \"ingredients\": [\n \"cream\",\n \"sugar\",\n \"vanilla\",\n \"leaf gelatine\"\n ]\n}\n\nANSWER FORMAT: exact:yes|no", "expected": { "value": "no" }, "samples": [ { "sample": 0, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 891, "output_tokens": 1, "latency_ms": 685.2, "usd": 0.00179, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 891, "output_tokens": 1, "latency_ms": 572.2, "usd": 0.00179, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 891, "output_tokens": 1, "latency_ms": 560.9, "usd": 0.00179, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 891.0, "output_tokens_mean": 1.0, "latency_ms_mean": 606.1, "usd_sum": 0.00537 } }, { "task_id": "ogs:core:benchmark-task:diet-004", "category": "dietary", "capability": "kosher_meat_dairy", "difficulty": "medium", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "85fc94958c4357ef", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nChicken parmigiana is breaded chicken breast topped with tomato sauce and melted mozzarella, served with a side of cream-rich garlic mashed potatoes. From a kosher perspective, what is the core violation? Respond with one short phrase.\n\nINPUT:\n{\n \"dish\": \"chicken parmigiana with creamy mash\"\n}\n\nANSWER FORMAT: exact:string", "expected": { "value": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "samples": [ { "sample": 0, "raw_response": "mixing meat and dairy", "compliant": true, "score": 1.0, "detail": { "predicted": "mixing meat and dairy", "expected": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "metrics": { "input_tokens": 885, "output_tokens": 5, "latency_ms": 511.4, "usd": 0.00181, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "mixing_meat_and_dairy", "compliant": true, "score": 0.0, "detail": { "predicted": "mixing_meat_and_dairy", "expected": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "metrics": { "input_tokens": 885, "output_tokens": 7, "latency_ms": 707.4, "usd": 0.001826, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "mixing meat and dairy", "compliant": true, "score": 1.0, "detail": { "predicted": "mixing meat and dairy", "expected": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "metrics": { "input_tokens": 885, "output_tokens": 5, "latency_ms": 693.5, "usd": 0.00181, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": 0.0133, "ci95_hi": 1.32, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 885.0, "output_tokens_mean": 5.667, "latency_ms_mean": 637.433, "usd_sum": 0.005446 } }, { "task_id": "ogs:core:benchmark-task:diet-005", "category": "dietary", "capability": "allergen_detection", "difficulty": "easy", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "f40f4c25a2ee4b71", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nFor a dish of pesto genovese made from basil, garlic, pine nuts, parmesan, pecorino, and olive oil, list the EU Annex II allergens that must be declared. Return a comma-separated list using the OGS allergen IDs.\n\nINPUT:\n{\n \"dish\": \"pesto genovese\",\n \"ingredients\": [\n \"basil\",\n \"garlic\",\n \"pine nuts\",\n \"parmesan\",\n \"pecorino\",\n \"olive oil\"\n ]\n}\n\nANSWER FORMAT: set:comma-separated OGS allergen IDs", "expected": { "values": [ "tree_nuts", "milk" ] }, "samples": [ { "sample": 0, "raw_response": "milk,tree_nuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "milk", "tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 934, "output_tokens": 5, "latency_ms": 637.9, "usd": 0.001908, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "milk,tree_nuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "milk", "tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 934, "output_tokens": 5, "latency_ms": 478.1, "usd": 0.001908, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "milk,tree_nuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "milk", "tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 934, "output_tokens": 5, "latency_ms": 590.6, "usd": 0.001908, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 934.0, "output_tokens_mean": 5.0, "latency_ms_mean": 568.867, "usd_sum": 0.005724 } }, { "task_id": "ogs:core:benchmark-task:diet-006", "category": "dietary", "capability": "allergen_detection", "difficulty": "medium", "cuisine_region": "thai", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "7f45e388301a68a5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nReturn the EU Annex II allergens that must be declared for a standard pad thai (rice noodles, shrimp, egg, tamarind, fish sauce, palm sugar, roasted peanuts, bean sprouts, garlic chives, lime, chili).\n\nINPUT:\n{\n \"dish\": \"pad thai\"\n}\n\nANSWER FORMAT: set:comma-separated OGS allergen IDs", "expected": { "values": [ "crustaceans", "eggs", "fish", "peanuts" ] }, "samples": [ { "sample": 0, "raw_response": "crustaceans,eggs,fish,peanuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "crustaceans", "eggs", "fish", "peanuts" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 888, "output_tokens": 12, "latency_ms": 638.0, "usd": 0.001872, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "crustaceans,eggs,fish,peanuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "crustaceans", "eggs", "fish", "peanuts" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 888, "output_tokens": 12, "latency_ms": 739.2, "usd": 0.001872, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "crustaceans,eggs,fish,peanuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "crustaceans", "eggs", "fish", "peanuts" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 888, "output_tokens": 12, "latency_ms": 642.4, "usd": 0.001872, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 888.0, "output_tokens_mean": 12.0, "latency_ms_mean": 673.2, "usd_sum": 0.005616 } }, { "task_id": "ogs:core:benchmark-task:diet-007", "category": "dietary", "capability": "vegan_substitution", "difficulty": "medium", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "eb092a2c162960f6", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nName a single plant-based ingredient commonly used to emulsify and thicken a vegan carbonara sauce in place of eggs, while also delivering umami. Respond with one short ingredient name.\n\nINPUT:\n{\n \"target_role\": \"egg emulsifier and umami in vegan carbonara\"\n}\n\nANSWER FORMAT: exact:string", "expected": { "value": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "samples": [ { "sample": 0, "raw_response": "tofu", "compliant": true, "score": 0.0, "detail": { "predicted": "tofu", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 880, "output_tokens": 2, "latency_ms": 614.9, "usd": 0.001776, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "miso", "compliant": true, "score": 0.0, "detail": { "predicted": "miso", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 880, "output_tokens": 2, "latency_ms": 759.5, "usd": 0.001776, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "miso", "compliant": true, "score": 0.0, "detail": { "predicted": "miso", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 880, "output_tokens": 2, "latency_ms": 596.5, "usd": 0.001776, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 880.0, "output_tokens_mean": 2.0, "latency_ms_mean": 656.967, "usd_sum": 0.005328 } }, { "task_id": "ogs:core:benchmark-task:diet-008", "category": "dietary", "capability": "gluten_free_substitution", "difficulty": "easy", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "480be99b3f35a51d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nSuggest a single widely-used gluten-free flour to make a béchamel roux that maintains classic texture. Respond with one word.\n\nINPUT:\n{\n \"target_role\": \"béchamel roux, gluten-free\"\n}\n\nANSWER FORMAT: exact:string", "expected": { "value": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "samples": [ { "sample": 0, "raw_response": "cornstarch", "compliant": true, "score": 1.0, "detail": { "predicted": "cornstarch", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 867, "output_tokens": 3, "latency_ms": 671.3, "usd": 0.001758, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "rice", "compliant": true, "score": 0.0, "detail": { "predicted": "rice", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 867, "output_tokens": 1, "latency_ms": 711.0, "usd": 0.001742, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cornflour", "compliant": true, "score": 1.0, "detail": { "predicted": "cornflour", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 867, "output_tokens": 3, "latency_ms": 694.5, "usd": 0.001758, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": 0.0133, "ci95_hi": 1.32, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 867.0, "output_tokens_mean": 2.333, "latency_ms_mean": 692.267, "usd_sum": 0.005258 } }, { "task_id": "ogs:core:benchmark-task:diet-009", "category": "dietary", "capability": "vegan_compatibility", "difficulty": "medium", "cuisine_region": "global", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "936752891554dba3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nFrom this list, return every item that is NOT vegan as a comma-separated list: honey, agave nectar, wine clarified with isinglass, wine clarified with bentonite, carmine, nutritional yeast, shellac, maple syrup, worcestershire sauce (traditional), vegetable glycerin.\n\nINPUT:\n{\n \"items\": [\n \"honey\",\n \"agave nectar\",\n \"wine clarified with isinglass\",\n \"wine clarified with bentonite\",\n \"carmine\",\n \"nutritional yeast\",\n \"shellac\",\n \"maple syrup\",\n \"worcestershire sauce (traditional)\",\n \"vegetable glycerin\"\n ]\n}\n\nANSWER FORMAT: set:comma-separated item names", "expected": { "values": [ "honey", "wine clarified with isinglass", "carmine", "shellac", "worcestershire sauce (traditional)" ] }, "samples": [ { "sample": 0, "raw_response": "honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 1.0, "detail": { "predicted": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 964, "output_tokens": 22, "latency_ms": 765.9, "usd": 0.002104, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 1.0, "detail": { "predicted": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 964, "output_tokens": 22, "latency_ms": 794.0, "usd": 0.002104, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 1.0, "detail": { "predicted": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 964, "output_tokens": 22, "latency_ms": 691.5, "usd": 0.002104, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 964.0, "output_tokens_mean": 22.0, "latency_ms_mean": 750.467, "usd_sum": 0.006312 } }, { "task_id": "ogs:core:benchmark-task:diet-010", "category": "dietary", "capability": "cross_contact_risk", "difficulty": "medium", "cuisine_region": "global", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "35c29846f76046d7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nA kitchen fries breaded calamari, battered cod, and french fries in a single deep fryer. Return the EU allergens that a customer ordering 'fries only' must be warned about as a comma-separated OGS allergen ID list.\n\nINPUT:\n{\n \"scenario\": \"single shared fryer\",\n \"items\": [\n \"breaded calamari\",\n \"battered cod\",\n \"french fries\"\n ]\n}\n\nANSWER FORMAT: set:comma-separated OGS allergen IDs", "expected": { "values": [ "molluscs", "fish", "cereals_containing_gluten" ] }, "samples": [ { "sample": 0, "raw_response": "crustaceans,fish,cereals_containing_gluten,eggs", "compliant": true, "score": 0.5714, "detail": { "predicted": [ "cereals_containing_gluten", "crustaceans", "eggs", "fish" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.5, "recall": 0.6667 }, "metrics": { "input_tokens": 916, "output_tokens": 16, "latency_ms": 662.8, "usd": 0.00196, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "crustaceans,fish,cereals_containing_gluten,eggs", "compliant": true, "score": 0.5714, "detail": { "predicted": [ "cereals_containing_gluten", "crustaceans", "eggs", "fish" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.5, "recall": 0.6667 }, "metrics": { "input_tokens": 916, "output_tokens": 16, "latency_ms": 757.4, "usd": 0.00196, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "crustaceans,fish,cereals_containing_gluten,eggs", "compliant": true, "score": 0.5714, "detail": { "predicted": [ "cereals_containing_gluten", "crustaceans", "eggs", "fish" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.5, "recall": 0.6667 }, "metrics": { "input_tokens": 916, "output_tokens": 16, "latency_ms": 642.2, "usd": 0.00196, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.5714, "score_summary": { "mean": 0.5714, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.5714, "ci95_hi": 0.5714, "n": 3 }, "score_if_valid": 0.5714, "format_rate": 1.0, "metrics": { "input_tokens_mean": 916.0, "output_tokens_mean": 16.0, "latency_ms_mean": 687.467, "usd_sum": 0.00588 } }, { "task_id": "ogs:core:benchmark-task:diet-011", "category": "dietary", "capability": "low_fodmap", "difficulty": "hard", "cuisine_region": "global", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "bdd7970997c11172", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nReturn the low-FODMAP violations in this dish as a comma-separated list of ingredient names: garlic-infused olive oil, white onion, lactose-free milk, wheat pasta, lean chicken, fresh chives, honey, aged parmesan.\n\nINPUT:\n{\n \"ingredients\": [\n \"garlic-infused olive oil\",\n \"white onion\",\n \"lactose-free milk\",\n \"wheat pasta\",\n \"lean chicken\",\n \"fresh chives\",\n \"honey\",\n \"aged parmesan\"\n ]\n}\n\nANSWER FORMAT: set:comma-separated ingredient names", "expected": { "values": [ "white onion", "wheat pasta", "honey" ] }, "samples": [ { "sample": 0, "raw_response": "white onion,wheat pasta,honey,aged parmesan", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "aged parmesan", "honey", "wheat pasta", "white onion" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 0.75, "recall": 1.0 }, "metrics": { "input_tokens": 933, "output_tokens": 10, "latency_ms": 660.5, "usd": 0.001946, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "white onion,wheat pasta,honey", "compliant": true, "score": 1.0, "detail": { "predicted": [ "honey", "wheat pasta", "white onion" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 933, "output_tokens": 7, "latency_ms": 1613.2, "usd": 0.001922, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "white onion,wheat pasta,honey", "compliant": true, "score": 1.0, "detail": { "predicted": [ "honey", "wheat pasta", "white onion" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 933, "output_tokens": 7, "latency_ms": 647.0, "usd": 0.001922, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.9524, "score_summary": { "mean": 0.9524, "stdev": 0.0825, "sem": 0.0476, "ci95_lo": 0.859, "ci95_hi": 1.0457, "n": 3 }, "score_if_valid": 0.9524, "format_rate": 1.0, "metrics": { "input_tokens_mean": 933.0, "output_tokens_mean": 8.0, "latency_ms_mean": 973.567, "usd_sum": 0.00579 } }, { "task_id": "ogs:core:benchmark-task:diet-012", "category": "dietary", "capability": "pescatarian_vs_vegetarian", "difficulty": "easy", "cuisine_region": "japanese", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "42c897d741064981", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nA dish contains miso, dashi (made with katsuobushi), tofu, and wakame. Mark which labels it qualifies for out of: vegan, vegetarian, pescatarian. Return a comma-separated list.\n\nINPUT:\n{\n \"dish\": \"classic awase-dashi miso soup with tofu and wakame\"\n}\n\nANSWER FORMAT: set:comma-separated labels", "expected": { "values": [ "pescatarian" ] }, "samples": [ { "sample": 0, "raw_response": "pescatarian", "compliant": true, "score": 1.0, "detail": { "predicted": [ "pescatarian" ], "expected": [ "pescatarian" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 893, "output_tokens": 4, "latency_ms": 621.2, "usd": 0.001818, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "pescatarian", "compliant": true, "score": 1.0, "detail": { "predicted": [ "pescatarian" ], "expected": [ "pescatarian" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 893, "output_tokens": 4, "latency_ms": 594.0, "usd": 0.001818, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "pescatarian", "compliant": true, "score": 1.0, "detail": { "predicted": [ "pescatarian" ], "expected": [ "pescatarian" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 893, "output_tokens": 4, "latency_ms": 654.5, "usd": 0.001818, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 893.0, "output_tokens_mean": 4.0, "latency_ms_mean": 623.233, "usd_sum": 0.005454 } }, { "task_id": "ogs:core:benchmark-task:menu-001", "category": "menu_engineering", "capability": "matrix_classification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "138c09ed611a2d43", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nA dish has above-average popularity and above-average contribution margin on the menu. Using the OGS menu-engineering matrix, which quadrant is it? Respond with one word.\n\nINPUT:\n{\n \"popularity\": \"above\",\n \"margin\": \"above\"\n}\n\nANSWER FORMAT: exact:star|plowhorse|puzzle|dog", "expected": { "value": "star" }, "samples": [ { "sample": 0, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 499, "output_tokens": 1, "latency_ms": 462.8, "usd": 0.001006, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 499, "output_tokens": 1, "latency_ms": 673.3, "usd": 0.001006, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 499, "output_tokens": 1, "latency_ms": 937.9, "usd": 0.001006, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 499.0, "output_tokens_mean": 1.0, "latency_ms_mean": 691.333, "usd_sum": 0.003018 } }, { "task_id": "ogs:core:benchmark-task:menu-002", "category": "menu_engineering", "capability": "matrix_classification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "b5df321fd829de76", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nA dish sells strongly but the contribution margin is below the menu average. Classify it.\n\nINPUT:\n{\n \"popularity\": \"above\",\n \"margin\": \"below\"\n}\n\nANSWER FORMAT: exact:star|plowhorse|puzzle|dog", "expected": { "value": "plowhorse" }, "samples": [ { "sample": 0, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 483, "output_tokens": 3, "latency_ms": 595.7, "usd": 0.00099, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 483, "output_tokens": 3, "latency_ms": 556.4, "usd": 0.00099, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 483, "output_tokens": 3, "latency_ms": 652.9, "usd": 0.00099, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 483.0, "output_tokens_mean": 3.0, "latency_ms_mean": 601.667, "usd_sum": 0.00297 } }, { "task_id": "ogs:core:benchmark-task:menu-003", "category": "menu_engineering", "capability": "matrix_classification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "9795b72bdda437f1", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nA dish has strong contribution margin but is rarely ordered. Classify it.\n\nINPUT:\n{\n \"popularity\": \"below\",\n \"margin\": \"above\"\n}\n\nANSWER FORMAT: exact:star|plowhorse|puzzle|dog", "expected": { "value": "puzzle" }, "samples": [ { "sample": 0, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 480, "output_tokens": 2, "latency_ms": 638.1, "usd": 0.000976, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 480, "output_tokens": 2, "latency_ms": 640.5, "usd": 0.000976, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 480, "output_tokens": 2, "latency_ms": 564.1, "usd": 0.000976, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 480.0, "output_tokens_mean": 2.0, "latency_ms_mean": 614.233, "usd_sum": 0.002928 } }, { "task_id": "ogs:core:benchmark-task:menu-004", "category": "menu_engineering", "capability": "matrix_classification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "fc0da6dcbbc842fb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nA dish is rarely ordered and has a contribution margin below the menu average. Classify it.\n\nINPUT:\n{\n \"popularity\": \"below\",\n \"margin\": \"below\"\n}\n\nANSWER FORMAT: exact:star|plowhorse|puzzle|dog", "expected": { "value": "dog" }, "samples": [ { "sample": 0, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 484, "output_tokens": 1, "latency_ms": 674.9, "usd": 0.000976, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 484, "output_tokens": 1, "latency_ms": 694.2, "usd": 0.000976, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 484, "output_tokens": 1, "latency_ms": 565.6, "usd": 0.000976, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 484.0, "output_tokens_mean": 1.0, "latency_ms_mean": 644.9, "usd_sum": 0.002928 } }, { "task_id": "ogs:core:benchmark-task:menu-005", "category": "menu_engineering", "capability": "food_cost", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "f33710f88f89121e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nA dish has a food cost of £4.20 and a menu price of £14.00. Return the food-cost percentage as a single integer.\n\nINPUT:\n{\n \"food_cost\": 4.2,\n \"menu_price\": 14.0\n}\n\nANSWER FORMAT: numeric:integer percent", "expected": { "value": 30, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "30", "compliant": true, "score": 1.0, "detail": { "predicted": 30.0, "expected": 30.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 493, "output_tokens": 1, "latency_ms": 650.1, "usd": 0.000994, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "30", "compliant": true, "score": 1.0, "detail": { "predicted": 30.0, "expected": 30.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 493, "output_tokens": 1, "latency_ms": 566.8, "usd": 0.000994, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "30", "compliant": true, "score": 1.0, "detail": { "predicted": 30.0, "expected": 30.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 493, "output_tokens": 1, "latency_ms": 777.2, "usd": 0.000994, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 493.0, "output_tokens_mean": 1.0, "latency_ms_mean": 664.7, "usd_sum": 0.002982 } }, { "task_id": "ogs:core:benchmark-task:menu-006", "category": "menu_engineering", "capability": "contribution_margin", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "7bb019ca9ca4b1be", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nA dish has a food cost of $6.50 and a menu price of $22.00. Return the contribution margin in dollars as a single number with two decimals.\n\nINPUT:\n{\n \"food_cost\": 6.5,\n \"menu_price\": 22.0\n}\n\nANSWER FORMAT: numeric:decimal USD", "expected": { "value": 15.5, "tolerance": 0.05 }, "samples": [ { "sample": 0, "raw_response": "15.50", "compliant": true, "score": 1.0, "detail": { "predicted": 15.5, "expected": 15.5, "tolerance": 0.05 }, "metrics": { "input_tokens": 497, "output_tokens": 3, "latency_ms": 726.3, "usd": 0.001018, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "15.50", "compliant": true, "score": 1.0, "detail": { "predicted": 15.5, "expected": 15.5, "tolerance": 0.05 }, "metrics": { "input_tokens": 497, "output_tokens": 3, "latency_ms": 745.6, "usd": 0.001018, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "15.50", "compliant": true, "score": 1.0, "detail": { "predicted": 15.5, "expected": 15.5, "tolerance": 0.05 }, "metrics": { "input_tokens": 497, "output_tokens": 3, "latency_ms": 480.7, "usd": 0.001018, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 497.0, "output_tokens_mean": 3.0, "latency_ms_mean": 650.867, "usd_sum": 0.003054 } }, { "task_id": "ogs:core:benchmark-task:menu-007", "category": "menu_engineering", "capability": "menu_rebalance", "difficulty": "hard", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "68b7fb2ec1e432f4", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nFive main courses have this (popularity %, margin $) profile: A (35, 18), B (30, 9), C (5, 6), D (20, 16), E (10, 7). Average popularity is 20%; average margin is $11.20. Which single dish is the dog? Respond with the letter only.\n\nINPUT:\n{\n \"dishes\": [\n {\n \"id\": \"A\",\n \"pop\": 35,\n \"margin\": 18\n },\n {\n \"id\": \"B\",\n \"pop\": 30,\n \"margin\": 9\n },\n {\n \"id\": \"C\",\n \"pop\": 5,\n \"margin\": 6\n },\n {\n \"id\": \"D\",\n \"pop\": 20,\n \"margin\": 16\n },\n {\n \"id\": \"E\",\n \"pop\": 10,\n \"margin\": 7\n }\n ],\n \"avg_pop\": 20,\n \"avg_margin\": 11.2\n}\n\nANSWER FORMAT: exact:A|B|C|D|E", "expected": { "value": "C" }, "samples": [ { "sample": 0, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 675, "output_tokens": 1, "latency_ms": 843.1, "usd": 0.001358, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 675, "output_tokens": 1, "latency_ms": 633.0, "usd": 0.001358, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 675, "output_tokens": 1, "latency_ms": 646.7, "usd": 0.001358, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 675.0, "output_tokens_mean": 1.0, "latency_ms_mean": 707.6, "usd_sum": 0.004074 } }, { "task_id": "ogs:core:benchmark-task:menu-008", "category": "menu_engineering", "capability": "target_price", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles" ], "prompt_template_hash": "dc5bf7ed3a0583c2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nA chef wants a 28% food cost on a dish whose ingredient cost is £3.92. Return the target menu price in pounds, two decimals.\n\nINPUT:\n{\n \"food_cost\": 3.92,\n \"target_food_cost_pct\": 28\n}\n\nANSWER FORMAT: numeric:decimal GBP", "expected": { "value": 14.0, "tolerance": 0.05 }, "samples": [ { "sample": 0, "raw_response": "14.00", "compliant": true, "score": 1.0, "detail": { "predicted": 14.0, "expected": 14.0, "tolerance": 0.05 }, "metrics": { "input_tokens": 494, "output_tokens": 3, "latency_ms": 659.1, "usd": 0.001012, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "14.00", "compliant": true, "score": 1.0, "detail": { "predicted": 14.0, "expected": 14.0, "tolerance": 0.05 }, "metrics": { "input_tokens": 494, "output_tokens": 3, "latency_ms": 605.9, "usd": 0.001012, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "14.00", "compliant": true, "score": 1.0, "detail": { "predicted": 14.0, "expected": 14.0, "tolerance": 0.05 }, "metrics": { "input_tokens": 494, "output_tokens": 3, "latency_ms": 612.3, "usd": 0.001012, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 494.0, "output_tokens_mean": 3.0, "latency_ms_mean": 625.767, "usd_sum": 0.003036 } }, { "task_id": "ogs:core:benchmark-task:menu-009", "category": "menu_engineering", "capability": "menu_critique", "difficulty": "hard", "cuisine_region": "global", "scorer": "rubric_judge", "context_needs": [ "rules.menu_engineering", "vocab.courses", "vocab.component_roles", "vocab.match_types", "rules.dietary", "rules.allergens_eu" ], "prompt_template_hash": "8883cacb0aca5024", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Menu engineering reference\n\nClassical Boston Matrix quadrants (popularity vs. contribution margin, each split at the menu average):\n- **Star**: high popularity, high margin → feature prominently, do not change.\n- **Plowhorse**: high popularity, low margin → redesign the dish to cut food cost or reprice gently.\n- **Puzzle**: low popularity, high margin → reposition on the menu, rename, or add a compelling description.\n- **Dog**: low popularity, low margin → remove or replace.\n\nContribution margin (CM) = menu price − food cost. Food-cost percentage = food cost / menu price. Industry target for casual dining: 28–35% food cost.\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n---\n\nCritique the following five-course autumn tasting menu. Identify at least two concrete weaknesses (flow, seasonality, allergen risk, cost-to-price ratio, or structural monotony), suggest one specific, constructive change, and justify each point in 3 short paragraphs. Avoid generic praise.\n\nINPUT:\n{\n \"menu\": [\n {\n \"course\": \"amuse\",\n \"dish\": \"pumpkin velouté, sage oil\"\n },\n {\n \"course\": \"appetizer\",\n \"dish\": \"butternut squash risotto, brown butter, amaretti crumble\"\n },\n {\n \"course\": \"fish\",\n \"dish\": \"pan-seared scallops, pumpkin purée, crispy pancetta\"\n },\n {\n \"course\": \"main\",\n \"dish\": \"roast pork loin, sweet potato purée, cider jus\"\n },\n {\n \"course\": \"dessert\",\n \"dish\": \"pumpkin cheesecake, spiced pecan brittle\"\n }\n ],\n \"target_food_cost_pct\": 30,\n \"dietary_constraints\": \"must offer a viable vegetarian and a viable nut-free path\"\n}\n\nANSWER FORMAT: free text, 3 short paragraphs", "expected": { "rubric": [ { "id": "diagnosis", "weight": 0.4, "description": "Identifies concrete, defensible weaknesses (flavor monotony from repeated pumpkin/squash, nut allergen in amaretti and pecans, heavy starches in consecutive courses).", "anchors": { "0.0": "No specific weakness identified.", "0.5": "Identifies one concrete weakness but misses another major one.", "1.0": "Identifies at least two of: pumpkin/squash repetition across 4 of 5 courses; nut allergen across amaretti and pecans; consecutive purée/starch heaviness." } }, { "id": "remediation", "weight": 0.3, "description": "Offers a specific, actionable, seasonally-plausible change that addresses the identified weakness.", "anchors": { "0.0": "No change proposed or change is vague.", "0.5": "Change is specific but does not address the main weakness.", "1.0": "Concrete substitute with named ingredient/technique (e.g. swap scallop course to cured mackerel with pickled apple)." } }, { "id": "justification", "weight": 0.3, "description": "Justification is grounded in OGS concepts (match types, structural balance, service flow) rather than marketing language.", "anchors": { "0.0": "Pure adjective salad.", "0.5": "Some reasoning, but appeals to authority not mechanism.", "1.0": "Explicitly cites a mechanism: intensity alignment, contrast, allergen cross-contact, food-cost math." } } ], "reference_answer": "Key weaknesses: (1) pumpkin/squash appears in 4 of 5 courses, collapsing the menu's flavour arc into a single beta-carotene/sweet-starch note; (2) the amaretti crumble (bitter almond) and the pecan brittle together block every nut-allergic guest from the tasting; (3) velouté, risotto, two purées and a cheesecake stack four viscous/starchy textures in a row with no acid or raw element. A concrete fix is to replace the scallop course with cured mackerel over pickled Granny Smith apple and wasabi-lime gel: it re-introduces sea/fruit/acid, breaks the texture loop, removes one pork-cross-contact dish, and simultaneously opens a pescatarian-friendly option. Justification: on OGS terms this swap adds a `contrast` match (acid/fat), raises `acidity_perception` mid-meal to refresh the palate before the roast, and removes one of the two tree-nut exposure points." }, "samples": [ { "sample": 0, "raw_response": "This menu exhibits structural monotony, with pumpkin or other orange-fleshed squashes appearing in four out of five courses: amuse (pumpkin), appetizer (butternut), fish (pumpkin), and dessert (pumpkin). This repetition limits both flavor diversity and guest excitement, risking palate fatigue and diminishing impact of seasonal produce. The lack of contrast between courses, especially frontloading with two similar squashes, dilutes the overall tasting experience.\n\nAllergen and dietary accommodation is another serious weakness. The appetizer features an amaretti crumble (usually containing almonds), while dessert contains pecans, preventing a nut-free path without substitutions. The menu also lacks a clear, compelling vegetarian path, as the scallops and pork cannot be simply omitted without significant reworking. This runs counter to the brief’s requirement for both nut-free and vegetarian alternatives to be built in at menu design stage.\n\nTo address these issues, replace the butternut squash risotto with a wild mushroom risotto featuring crispy kale and a parmesan tuile. This change breaks the repetitive orange squash motif, introduces appealing autumnal flavors, and, if the parmesan tuile is nut-free, restores a nut-free option. It also provides a satisfying vegetarian dish that integrates more easily with the menu as a whole, enhancing both the guest experience and compliance with requirements.", "compliant": true, "score": 0.88, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies two major concrete weaknesses: repeated pumpkin/squash across four courses and the nut-free/vegetarian path failure from amaretti, pecans, scallops, and pork." }, { "id": "remediation", "weight": 0.3, "score": 0.8, "note": "The proposed swap to wild mushroom risotto with crispy kale and parmesan tuile is specific and seasonal, though it addresses repetition and vegetarianity more than the broader structural heaviness or dessert nut issue." }, { "id": "justification", "weight": 0.3, "score": 0.8, "note": "The reasoning cites palate fatigue, lack of contrast, and menu-design-stage accommodation mechanics, but it does not discuss service flow, texture sequencing, or food-cost implications in much depth." } ], "summary": "The answer follows the required three-paragraph free-text format and avoids generic praise. It gives a strong diagnosis with concrete menu-design weaknesses and a plausible seasonal fix, though its justification could be more explicitly grounded in structural flow and cost/allergen mechanics across the full menu.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1252, "output_tokens": 264, "latency_ms": 3437.3, "usd": 0.004616, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "This menu exhibits structural monotony and ingredient repetition, particularly around pumpkin and other sweet squashes. Four out of five courses feature pumpkin or butternut squash, blurring transitions between courses and leading to palate fatigue. The repetition detracts from the sense of progression and surprise expected in a tasting format.\n\nThere is also a significant allergen risk and lack of flexibility for dietary accommodations. The amaretti crumble in the risotto and the pecan brittle in the dessert both introduce tree nuts, making it difficult to offer a nut-free path without omitting key textural elements. Furthermore, only one course (the amuse) is naturally vegetarian—scallops and pork limit the viability of a vegetarian progression, requiring drastic substitutions that could disrupt menu balance.\n\nTo improve both structural flow and allergen accessibility, replace the butternut squash risotto (appetizer) with a roasted beet tartare with horseradish crème and sunflower seed gremolata. This alternative is visually striking, maintains autumnality without repeating squash, and can be made both vegetarian and nut-free while preserving texture and richness. Such a change improves both menu variety and inclusivity.", "compliant": true, "score": 0.94, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies two major weaknesses from the rubric: repeated pumpkin/squash across most courses and nut-allergen plus vegetarian-path problems." }, { "id": "remediation", "weight": 0.3, "score": 1.0, "note": "It proposes a concrete, seasonally plausible substitution with named ingredients and technique that directly reduces squash repetition and supports vegetarian/nut-free service." }, { "id": "justification", "weight": 0.3, "score": 0.8, "note": "The reasoning explains palate fatigue, course progression, and dietary accessibility mechanisms, though it is lighter on explicit service-flow or food-cost analysis." } ], "summary": "The answer follows the required three-paragraph free-text format and avoids generic praise. It diagnoses multiple concrete menu flaws and offers a specific autumnal replacement that addresses repetition and dietary constraints, with solid though not maximally technical justification.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1252, "output_tokens": 230, "latency_ms": 2812.0, "usd": 0.004344, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "This menu reveals an issue of structural monotony and flavor repetitiveness, with pumpkin or squash featured in four out of five courses (amuse, appetizer, fish, and dessert). Such heavy reliance on a single vegetable creates palate fatigue and limits the perceived creativity of the menu, especially in a tasting format where guests expect variety across courses. This repetition also narrows the aromatic and visual palette of the meal, making each course feel less distinct.\n\nSecondly, the menu fails to provide a viable nut-free path: the appetizer uses amaretti (which may contain almonds, a tree_nuts allergen), and the dessert includes pecan brittle (also tree_nuts). This exclusion prevents nut-allergic guests from participating fully in at least two courses, contradicting the stated dietary constraint. The use of scallops and pancetta, plus the lack of vegetarian alternatives listed for the fish and main, also means the menu isn’t clear about its vegetarian options, making it challenging to offer an alternative path as required.\n\nOne constructive change is to replace the butternut squash risotto with a wild mushroom risotto, omitting the amaretti crumble, and to substitute the spiced pecan brittle in the dessert with pumpkin seed brittle. These adjustments reduce menu monotony by introducing new autumnal flavors (mushrooms, seeds), increase textural variety, and eliminate tree_nuts allergens, thus fulfilling the nut-free path requirement while enriching the menu’s overall flow and appeal.", "compliant": true, "score": 0.88, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies pumpkin/squash repetition and the nut-allergen problem, and also notes unclear vegetarian viability." }, { "id": "remediation", "weight": 0.3, "score": 0.8, "note": "It proposes concrete substitutions with named ingredients, though the changes focus more on allergen and repetition than on the menu's heavier texture flow." }, { "id": "justification", "weight": 0.3, "score": 0.8, "note": "The reasoning cites palate fatigue, exclusion of nut-allergic guests, and menu flow effects, though it is lighter on explicit service-flow or food-cost mechanics." } ], "summary": "The answer follows the requested three-paragraph free-text format and avoids generic praise. It diagnoses two major weaknesses well and offers specific seasonal fixes, with solid but not maximally technical justification grounded in menu balance and dietary access.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1252, "output_tokens": 293, "latency_ms": 2758.1, "usd": 0.004848, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.9, "score_summary": { "mean": 0.9, "stdev": 0.0346, "sem": 0.02, "ci95_lo": 0.8608, "ci95_hi": 0.9392, "n": 3 }, "score_if_valid": 0.9, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1252.0, "output_tokens_mean": 262.333, "latency_ms_mean": 3002.467, "usd_sum": 0.013808 } }, { "task_id": "ogs:core:benchmark-task:ml-ar-001", "category": "vocabulary", "capability": "ingredient_classification", "difficulty": "easy", "cuisine_region": "middle_eastern", "scorer": "exact_match", "context_needs": [ "vocab.ingredient_categories" ], "prompt_template_hash": "94e19d81d80368a1", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n---\n\nباستخدام مفردات OGS لتصنيفات المكونات، صنّف الزعتر بكلمة واحدة.\n\nINPUT:\n{\n \"item\": \"زعتر\"\n}\n\nANSWER FORMAT: one_of:protein,vegetable,fruit,grain,dairy,fat,herb,spice,fungus,legume,nut,seed,sweetener,acid,salt,other", "expected": { "value": "herb", "aliases": [ "spice" ] }, "samples": [ { "sample": 0, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 343, "output_tokens": 2, "latency_ms": 460.6, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 343, "output_tokens": 2, "latency_ms": 442.9, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 343, "output_tokens": 2, "latency_ms": 574.1, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 343.0, "output_tokens_mean": 2.0, "latency_ms_mean": 492.533, "usd_sum": 0.002106 } }, { "task_id": "ogs:core:benchmark-task:ml-ar-002", "category": "regional", "capability": "region_identification", "difficulty": "easy", "cuisine_region": "middle_eastern", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "6b39ec376be689ad", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nالمنسف هو الطبق الوطني لأي بلد عربي؟ أجب بكلمة واحدة.\n\nINPUT:\n{\n \"dish\": \"المنسف\"\n}\n\nANSWER FORMAT: exact:country", "expected": { "value": "jordan", "aliases": [ "الأردن", "jordan (الأردن)" ] }, "samples": [ { "sample": 0, "raw_response": "الأردن", "compliant": true, "score": 1.0, "detail": { "predicted": "الأردن", "expected": "jordan", "aliases": [ "الأردن", "jordan (الأردن)" ] }, "metrics": { "input_tokens": 260, "output_tokens": 3, "latency_ms": 642.0, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "الأردن", "compliant": true, "score": 1.0, "detail": { "predicted": "الأردن", "expected": "jordan", "aliases": [ "الأردن", "jordan (الأردن)" ] }, "metrics": { "input_tokens": 260, "output_tokens": 3, "latency_ms": 729.0, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "الأردن", "compliant": true, "score": 1.0, "detail": { "predicted": "الأردن", "expected": "jordan", "aliases": [ "الأردن", "jordan (الأردن)" ] }, "metrics": { "input_tokens": 260, "output_tokens": 3, "latency_ms": 702.4, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 260.0, "output_tokens_mean": 3.0, "latency_ms_mean": 691.133, "usd_sum": 0.001632 } }, { "task_id": "ogs:core:benchmark-task:ml-es-001", "category": "regional", "capability": "region_identification", "difficulty": "easy", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "5fe5c7f1f85e3675", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nEl pulpo a feira es un plato tradicional de qué región de España? Responde con una palabra.\n\nINPUT:\n{\n \"dish\": \"pulpo a feira\"\n}\n\nANSWER FORMAT: exact:region name", "expected": { "value": "galicia", "aliases": [ "galícia", "galiza" ] }, "samples": [ { "sample": 0, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 264, "output_tokens": 2, "latency_ms": 533.8, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 264, "output_tokens": 2, "latency_ms": 573.7, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 264, "output_tokens": 2, "latency_ms": 776.8, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 264.0, "output_tokens_mean": 2.0, "latency_ms_mean": 628.1, "usd_sum": 0.001632 } }, { "task_id": "ogs:core:benchmark-task:ml-es-002", "category": "vocabulary", "capability": "cooking_method_classification", "difficulty": "easy", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "9f03b90711bec40f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nUsando el vocabulario OGS de métodos de cocción, ¿cuál describe mejor la preparación clásica del cochinillo segoviano? Responde con una palabra.\n\nINPUT:\n{\n \"item\": \"cochinillo segoviano\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "roasted" }, "samples": [ { "sample": 0, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 397, "output_tokens": 2, "latency_ms": 665.0, "usd": 0.00081, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 397, "output_tokens": 2, "latency_ms": 625.8, "usd": 0.00081, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 397, "output_tokens": 2, "latency_ms": 628.8, "usd": 0.00081, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 397.0, "output_tokens_mean": 2.0, "latency_ms_mean": 639.867, "usd_sum": 0.00243 } }, { "task_id": "ogs:core:benchmark-task:ml-fr-001", "category": "regional", "capability": "region_identification", "difficulty": "easy", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "8d252ae3fb170e15", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nLa bouillabaisse est une préparation traditionnelle de quelle ville française ? Répondez par un mot.\n\nINPUT:\n{\n \"dish\": \"bouillabaisse\"\n}\n\nANSWER FORMAT: exact:city name", "expected": { "value": "marseille" }, "samples": [ { "sample": 0, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 264, "output_tokens": 2, "latency_ms": 609.0, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 264, "output_tokens": 2, "latency_ms": 773.4, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 264, "output_tokens": 2, "latency_ms": 623.9, "usd": 0.000544, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 264.0, "output_tokens_mean": 2.0, "latency_ms_mean": 668.767, "usd_sum": 0.001632 } }, { "task_id": "ogs:core:benchmark-task:ml-fr-002", "category": "sensory", "capability": "basic_tastes_profile", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "96a07aeab44536ab", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nPour une sauce beurre blanc classique, donnez le profil sur l'échelle OGS des cinq saveurs [sweet, sour, salty, bitter, umami] sous la forme d'un tableau JSON de cinq nombres entre 0 et 10.\n\nINPUT:\n{\n \"dish\": \"sauce beurre blanc classique\"\n}\n\nANSWER FORMAT: json:array of 5 numbers", "expected": { "values": [ 1, 5, 4, 1, 3 ] }, "samples": [ { "sample": 0, "raw_response": "[1.5, 5, 3, 0.5, 2]", "compliant": true, "score": 0.6, "detail": { "per_position": [ { "index": 0, "predicted": 1.5, "expected": 1, "score": 0.6667 }, { "index": 1, "predicted": 5, "expected": 5, "score": 1.0 }, { "index": 2, "predicted": 3, "expected": 4, "score": 0.3333 }, { "index": 3, "predicted": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 2, "expected": 3, "score": 0.3333 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 373, "output_tokens": 19, "latency_ms": 793.9, "usd": 0.000898, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[2, 4.5, 3.5, 0.5, 2]", "compliant": true, "score": 0.5333, "detail": { "per_position": [ { "index": 0, "predicted": 2, "expected": 1, "score": 0.3333 }, { "index": 1, "predicted": 4.5, "expected": 5, "score": 0.6667 }, { "index": 2, "predicted": 3.5, "expected": 4, "score": 0.6667 }, { "index": 3, "predicted": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 2, "expected": 3, "score": 0.3333 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 373, "output_tokens": 21, "latency_ms": 748.0, "usd": 0.000914, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[2, 5.5, 4, 1, 2]", "compliant": true, "score": 0.6667, "detail": { "per_position": [ { "index": 0, "predicted": 2, "expected": 1, "score": 0.3333 }, { "index": 1, "predicted": 5.5, "expected": 5, "score": 0.6667 }, { "index": 2, "predicted": 4, "expected": 4, "score": 1.0 }, { "index": 3, "predicted": 1, "expected": 1, "score": 1.0 }, { "index": 4, "predicted": 2, "expected": 3, "score": 0.3333 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 373, "output_tokens": 17, "latency_ms": 678.4, "usd": 0.000882, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6, "score_summary": { "mean": 0.6, "stdev": 0.0667, "sem": 0.0385, "ci95_lo": 0.5245, "ci95_hi": 0.6755, "n": 3 }, "score_if_valid": 0.6, "format_rate": 1.0, "metrics": { "input_tokens_mean": 373.0, "output_tokens_mean": 19.0, "latency_ms_mean": 740.1, "usd_sum": 0.002694 } }, { "task_id": "ogs:core:benchmark-task:ml-it-001", "category": "regional", "capability": "region_identification", "difficulty": "easy", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "c3aae88ebfcbe08b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nI pici sono una pasta fresca tipica di quale regione italiana? Rispondi con una parola.\n\nINPUT:\n{\n \"dish\": \"pici cacio e pepe\"\n}\n\nANSWER FORMAT: exact:regione", "expected": { "value": "toscana" }, "samples": [ { "sample": 0, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 266, "output_tokens": 3, "latency_ms": 563.5, "usd": 0.000556, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 266, "output_tokens": 3, "latency_ms": 605.3, "usd": 0.000556, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 266, "output_tokens": 3, "latency_ms": 507.3, "usd": 0.000556, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 266.0, "output_tokens_mean": 3.0, "latency_ms_mean": 558.7, "usd_sum": 0.001668 } }, { "task_id": "ogs:core:benchmark-task:ml-it-002", "category": "pairing", "capability": "beverage_selection", "difficulty": "medium", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "vocab.beverage_types", "vocab.match_types" ], "prompt_template_hash": "30919f613b1fbcd6", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nScegli l'abbinamento più classico per l'ossobuco alla milanese fra: barolo, riesling, prosecco, lambrusco. Rispondi con una parola.\n\nINPUT:\n{\n \"dish\": \"ossobuco alla milanese\"\n}\n\nANSWER FORMAT: exact:one of the given options", "expected": { "value": "barolo" }, "samples": [ { "sample": 0, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 2, "latency_ms": 587.1, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 2, "latency_ms": 612.2, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 2, "latency_ms": 951.1, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 329.0, "output_tokens_mean": 2.0, "latency_ms_mean": 716.8, "usd_sum": 0.002022 } }, { "task_id": "ogs:core:benchmark-task:ml-ja-001", "category": "vocabulary", "capability": "aromatic_family_classification", "difficulty": "easy", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "ff1f43723314705c", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nOGSの香りファミリー一覧から、柚子（ゆず）の主たる香りファミリーを一語で答えてください。\n\nINPUT:\n{\n \"item\": \"柚子\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "fruit" }, "samples": [ { "sample": 0, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 1, "latency_ms": 642.4, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 1, "latency_ms": 606.5, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 1, "latency_ms": 552.9, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 333.0, "output_tokens_mean": 1.0, "latency_ms_mean": 600.6, "usd_sum": 0.002022 } }, { "task_id": "ogs:core:benchmark-task:ml-ja-002", "category": "pairing", "capability": "beverage_selection", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "vocab.beverage_types", "vocab.match_types" ], "prompt_template_hash": "f68d4882814e0ecf", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\n握り寿司（赤身・白身・光物）のコース全体に最も安全に合う飲料のタイプを、次から一つ選んでください: sake, red_wine, stout_beer, bourbon.\n\nINPUT:\n{\n \"dish\": \"握り寿司コース\"\n}\n\nANSWER FORMAT: exact:one of the given options", "expected": { "value": "sake" }, "samples": [ { "sample": 0, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 2, "latency_ms": 576.8, "usd": 0.000694, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 2, "latency_ms": 593.1, "usd": 0.000694, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 2, "latency_ms": 613.3, "usd": 0.000694, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 339.0, "output_tokens_mean": 2.0, "latency_ms_mean": 594.4, "usd_sum": 0.002082 } }, { "task_id": "ogs:core:benchmark-task:nut-001", "category": "nutrition", "capability": "energy_calculation", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "94fadc6f5c8c5968", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA portion contains 40 g carbohydrate, 20 g protein, 15 g fat. Return total energy in kcal as a single integer, using the EU Annex XIV macro factors.\n\nINPUT:\n{\n \"carb_g\": 40,\n \"protein_g\": 20,\n \"fat_g\": 15\n}\n\nANSWER FORMAT: numeric:integer kcal", "expected": { "value": 375, "tolerance": 5 }, "samples": [ { "sample": 0, "raw_response": "385", "compliant": true, "score": 0.0, "detail": { "predicted": 385.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 816, "output_tokens": 1, "latency_ms": 595.0, "usd": 0.00164, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "385", "compliant": true, "score": 0.0, "detail": { "predicted": 385.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 816, "output_tokens": 1, "latency_ms": 521.6, "usd": 0.00164, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "365", "compliant": true, "score": 0.0, "detail": { "predicted": 365.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 816, "output_tokens": 1, "latency_ms": 575.2, "usd": 0.00164, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 816.0, "output_tokens_mean": 1.0, "latency_ms_mean": 563.933, "usd_sum": 0.00492 } }, { "task_id": "ogs:core:benchmark-task:nut-002", "category": "nutrition", "capability": "energy_calculation", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "4b141daaadd9af57", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA 150 mL glass of red wine contains approximately 14 g alcohol, 4 g carbohydrate, no protein, no fat. Return energy in kcal as a single integer.\n\nINPUT:\n{\n \"carb_g\": 4,\n \"protein_g\": 0,\n \"fat_g\": 0,\n \"alcohol_g\": 14\n}\n\nANSWER FORMAT: numeric:integer kcal", "expected": { "value": 114, "tolerance": 5 }, "samples": [ { "sample": 0, "raw_response": "114", "compliant": true, "score": 1.0, "detail": { "predicted": 114.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 825, "output_tokens": 1, "latency_ms": 818.7, "usd": 0.001658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "122", "compliant": true, "score": 0.0, "detail": { "predicted": 122.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 825, "output_tokens": 1, "latency_ms": 578.1, "usd": 0.001658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "122", "compliant": true, "score": 0.0, "detail": { "predicted": 122.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 825, "output_tokens": 1, "latency_ms": 557.7, "usd": 0.001658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": -0.32, "ci95_hi": 0.9867, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 825.0, "output_tokens_mean": 1.0, "latency_ms_mean": 651.5, "usd_sum": 0.004974 } }, { "task_id": "ogs:core:benchmark-task:nut-003", "category": "nutrition", "capability": "per_100g_estimate", "difficulty": "medium", "cuisine_region": "mediterranean", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "518ee70ef096f9ec", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA simple olive-oil vinaigrette is 75 g olive oil + 25 g red wine vinegar (vinegar ≈ 20 kcal/100 g). Return energy per 100 g of finished dressing as a single integer kcal.\n\nINPUT:\n{\n \"olive_oil_g\": 75,\n \"vinegar_g\": 25\n}\n\nANSWER FORMAT: numeric:integer kcal per 100 g", "expected": { "value": 668, "tolerance": 15 }, "samples": [ { "sample": 0, "raw_response": "673", "compliant": true, "score": 0.6667, "detail": { "predicted": 673.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 826, "output_tokens": 1, "latency_ms": 773.0, "usd": 0.00166, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "670", "compliant": true, "score": 0.8667, "detail": { "predicted": 670.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 826, "output_tokens": 1, "latency_ms": 513.9, "usd": 0.00166, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "673", "compliant": true, "score": 0.6667, "detail": { "predicted": 673.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 826, "output_tokens": 1, "latency_ms": 451.4, "usd": 0.00166, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7334, "score_summary": { "mean": 0.7334, "stdev": 0.1155, "sem": 0.0667, "ci95_lo": 0.6027, "ci95_hi": 0.864, "n": 3 }, "score_if_valid": 0.7334, "format_rate": 1.0, "metrics": { "input_tokens_mean": 826.0, "output_tokens_mean": 1.0, "latency_ms_mean": 579.433, "usd_sum": 0.00498 } }, { "task_id": "ogs:core:benchmark-task:nut-004", "category": "nutrition", "capability": "protein_estimate", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "42947503c82b308d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nEstimate the protein (g) in a 180 g cooked portion of skinless chicken-breast filet assuming 30% cooking mass loss. Respond with one integer.\n\nINPUT:\n{\n \"raw_mass_g_target_cooked\": 180,\n \"cooking_loss\": 0.3\n}\n\nANSWER FORMAT: numeric:integer g", "expected": { "value": 59, "tolerance": 4 }, "samples": [ { "sample": 0, "raw_response": "59", "compliant": true, "score": 1.0, "detail": { "predicted": 59.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 812, "output_tokens": 1, "latency_ms": 685.1, "usd": 0.001632, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "59", "compliant": true, "score": 1.0, "detail": { "predicted": 59.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 812, "output_tokens": 1, "latency_ms": 1091.9, "usd": 0.001632, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "41", "compliant": true, "score": 0.0, "detail": { "predicted": 41.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 812, "output_tokens": 1, "latency_ms": 612.7, "usd": 0.001632, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": 0.0133, "ci95_hi": 1.32, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 812.0, "output_tokens_mean": 1.0, "latency_ms_mean": 796.567, "usd_sum": 0.004896 } }, { "task_id": "ogs:core:benchmark-task:nut-005", "category": "nutrition", "capability": "macro_vector", "difficulty": "hard", "cuisine_region": "italian", "scorer": "numeric_vector_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "375ca5d44d346632", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA portion contains 85 g dry pasta (75 C / 13 P / 1.5 F per 100 g), 10 g butter (0.1 C / 0.9 P / 81 F per 100 g) and 15 g parmesan (3.2 C / 35 P / 29 F per 100 g). Return [carb_g, protein_g, fat_g, kcal] for the portion as a JSON array of four numbers.\n\nINPUT:\n{\n \"pasta_g\": 85,\n \"butter_g\": 10,\n \"parmesan_g\": 15\n}\n\nANSWER FORMAT: json:array [carb, protein, fat, kcal]", "expected": { "values": [ 64.3, 16.3, 13.7, 446 ] }, "samples": [ { "sample": 0, "raw_response": "[66.04, 13.43, 12.49, 474]", "compliant": true, "score": 0.265, "detail": { "per_position": [ { "index": 0, "predicted": 66.04, "expected": 64.3, "score": 0.42 }, { "index": 1, "predicted": 13.43, "expected": 16.3, "score": 0.0433 }, { "index": 2, "predicted": 12.49, "expected": 13.7, "score": 0.5967 }, { "index": 3, "predicted": 474, "expected": 446, "score": 0.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 890, "output_tokens": 18, "latency_ms": 716.8, "usd": 0.001924, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[66.56, 13.22, 10.85, 455]", "compliant": true, "score": 0.0742, "detail": { "per_position": [ { "index": 0, "predicted": 66.56, "expected": 64.3, "score": 0.2467 }, { "index": 1, "predicted": 13.22, "expected": 16.3, "score": 0.0 }, { "index": 2, "predicted": 10.85, "expected": 13.7, "score": 0.05 }, { "index": 3, "predicted": 455, "expected": 446, "score": 0.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 890, "output_tokens": 18, "latency_ms": 661.3, "usd": 0.001924, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[66.33, 13.9, 13.63, 506]", "compliant": true, "score": 0.375, "detail": { "per_position": [ { "index": 0, "predicted": 66.33, "expected": 64.3, "score": 0.3233 }, { "index": 1, "predicted": 13.9, "expected": 16.3, "score": 0.2 }, { "index": 2, "predicted": 13.63, "expected": 13.7, "score": 0.9767 }, { "index": 3, "predicted": 506, "expected": 446, "score": 0.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 890, "output_tokens": 18, "latency_ms": 751.1, "usd": 0.001924, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.2381, "score_summary": { "mean": 0.2381, "stdev": 0.1522, "sem": 0.0879, "ci95_lo": 0.0658, "ci95_hi": 0.4103, "n": 3 }, "score_if_valid": 0.2381, "format_rate": 1.0, "metrics": { "input_tokens_mean": 890.0, "output_tokens_mean": 18.0, "latency_ms_mean": 709.733, "usd_sum": 0.005772 } }, { "task_id": "ogs:core:benchmark-task:nut-006", "category": "nutrition", "capability": "energy_calculation", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "1ba6175ed99ad486", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA mocktail uses 180 mL fresh orange juice (approx 9 g carbohydrate per 100 g) plus 12 g granulated sugar. Return kcal as a single integer.\n\nINPUT:\n{\n \"oj_ml\": 180,\n \"sugar_g\": 12\n}\n\nANSWER FORMAT: numeric:integer kcal", "expected": { "value": 111, "tolerance": 6 }, "samples": [ { "sample": 0, "raw_response": "81", "compliant": true, "score": 0.0, "detail": { "predicted": 81.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 809, "output_tokens": 1, "latency_ms": 760.1, "usd": 0.001626, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "87", "compliant": true, "score": 0.0, "detail": { "predicted": 87.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 809, "output_tokens": 1, "latency_ms": 630.0, "usd": 0.001626, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "86", "compliant": true, "score": 0.0, "detail": { "predicted": 86.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 809, "output_tokens": 1, "latency_ms": 591.1, "usd": 0.001626, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 809.0, "output_tokens_mean": 1.0, "latency_ms_mean": 660.4, "usd_sum": 0.004878 } }, { "task_id": "ogs:core:benchmark-task:nut-007", "category": "nutrition", "capability": "fibre_rule", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "b9e5625ed0828c94", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nWhat kcal/g factor does the OGS nutrition reference assign to dietary fibre? Respond with a single number.\n\nANSWER FORMAT: numeric:decimal kcal/g", "expected": { "value": 2, "tolerance": 0.1 }, "samples": [ { "sample": 0, "raw_response": "2.0", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.1 }, "metrics": { "input_tokens": 773, "output_tokens": 3, "latency_ms": 508.2, "usd": 0.00157, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.1 }, "metrics": { "input_tokens": 773, "output_tokens": 1, "latency_ms": 584.6, "usd": 0.001554, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "2.0", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.1 }, "metrics": { "input_tokens": 773, "output_tokens": 3, "latency_ms": 676.9, "usd": 0.00157, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 773.0, "output_tokens_mean": 2.333, "latency_ms_mean": 589.9, "usd_sum": 0.004694 } }, { "task_id": "ogs:core:benchmark-task:nut-008", "category": "nutrition", "capability": "kj_conversion", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "95ef839d58e96bbc", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nConvert 250 kcal to kJ using the canonical OGS/EU conversion factor. Respond with a single integer.\n\nINPUT:\n{\n \"kcal\": 250\n}\n\nANSWER FORMAT: numeric:integer kJ", "expected": { "value": 1046, "tolerance": 10 }, "samples": [ { "sample": 0, "raw_response": "1046", "compliant": true, "score": 1.0, "detail": { "predicted": 1046.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 787, "output_tokens": 2, "latency_ms": 1119.6, "usd": 0.00159, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "1045", "compliant": true, "score": 0.9, "detail": { "predicted": 1045.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 787, "output_tokens": 2, "latency_ms": 671.7, "usd": 0.00159, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "1045", "compliant": true, "score": 0.9, "detail": { "predicted": 1045.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 787, "output_tokens": 2, "latency_ms": 582.5, "usd": 0.00159, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.9333, "score_summary": { "mean": 0.9333, "stdev": 0.0577, "sem": 0.0333, "ci95_lo": 0.868, "ci95_hi": 0.9987, "n": 3 }, "score_if_valid": 0.9333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 787.0, "output_tokens_mean": 2.0, "latency_ms_mean": 791.267, "usd_sum": 0.00477 } }, { "task_id": "ogs:core:benchmark-task:nut-009", "category": "nutrition", "capability": "macro_vector", "difficulty": "hard", "cuisine_region": "italian", "scorer": "numeric_vector_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "641416c8b33c6dbc", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA simple Alfredo sauce is 100 g butter + 150 g heavy cream (36% fat: 2.8 C / 2 P / 37 F) + 60 g parmesan (3.2 C / 35 P / 29 F), reduced to 250 g finished weight. Return [carb_per100g, protein_per100g, fat_per100g, kcal_per100g] as a JSON array of four numbers.\n\nINPUT:\n{\n \"butter_g\": 100,\n \"cream_g\": 150,\n \"parmesan_g\": 60,\n \"finished_g\": 250\n}\n\nANSWER FORMAT: json:array [carb, protein, fat, kcal] per 100 g", "expected": { "values": [ 2.5, 9.6, 55.2, 545 ] }, "samples": [ { "sample": 0, "raw_response": "[2.6, 7.2, 28.6, 298]", "compliant": true, "score": 0.3438, "detail": { "per_position": [ { "index": 0, "predicted": 2.6, "expected": 2.5, "score": 0.975 }, { "index": 1, "predicted": 7.2, "expected": 9.6, "score": 0.4 }, { "index": 2, "predicted": 28.6, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 298, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 895, "output_tokens": 18, "latency_ms": 741.6, "usd": 0.001934, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[2.1, 9.3, 32.6, 334]", "compliant": true, "score": 0.4563, "detail": { "per_position": [ { "index": 0, "predicted": 2.1, "expected": 2.5, "score": 0.9 }, { "index": 1, "predicted": 9.3, "expected": 9.6, "score": 0.925 }, { "index": 2, "predicted": 32.6, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 334, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 895, "output_tokens": 18, "latency_ms": 692.8, "usd": 0.001934, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[2.6, 10.8, 28.9, 323]", "compliant": true, "score": 0.4187, "detail": { "per_position": [ { "index": 0, "predicted": 2.6, "expected": 2.5, "score": 0.975 }, { "index": 1, "predicted": 10.8, "expected": 9.6, "score": 0.7 }, { "index": 2, "predicted": 28.9, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 323, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 895, "output_tokens": 18, "latency_ms": 821.5, "usd": 0.001934, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.4063, "score_summary": { "mean": 0.4063, "stdev": 0.0573, "sem": 0.0331, "ci95_lo": 0.3415, "ci95_hi": 0.4711, "n": 3 }, "score_if_valid": 0.4063, "format_rate": 1.0, "metrics": { "input_tokens_mean": 895.0, "output_tokens_mean": 18.0, "latency_ms_mean": 751.967, "usd_sum": 0.005802 } }, { "task_id": "ogs:core:benchmark-task:nut-010", "category": "nutrition", "capability": "numeric_compare", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "fd7edc20921469ff", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nFrom the set {olive oil, butter, granulated sugar, dry pasta}, return the ingredient with the highest kcal per gram. Respond with one short name.\n\nINPUT:\n{\n \"set\": [\n \"olive oil\",\n \"butter\",\n \"granulated sugar\",\n \"dry pasta\"\n ]\n}\n\nANSWER FORMAT: exact:string", "expected": { "value": "olive oil", "aliases": [ "olive-oil" ] }, "samples": [ { "sample": 0, "raw_response": "olive oil", "compliant": true, "score": 1.0, "detail": { "predicted": "olive oil", "expected": "olive oil", "aliases": [ "olive-oil" ] }, "metrics": { "input_tokens": 813, "output_tokens": 2, "latency_ms": 561.7, "usd": 0.001642, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "olive oil", "compliant": true, "score": 1.0, "detail": { "predicted": "olive oil", "expected": "olive oil", "aliases": [ "olive-oil" ] }, "metrics": { "input_tokens": 813, "output_tokens": 2, "latency_ms": 633.2, "usd": 0.001642, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "olive oil", "compliant": true, "score": 1.0, "detail": { "predicted": "olive oil", "expected": "olive oil", "aliases": [ "olive-oil" ] }, "metrics": { "input_tokens": 813, "output_tokens": 2, "latency_ms": 1078.4, "usd": 0.001642, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 813.0, "output_tokens_mean": 2.0, "latency_ms_mean": 757.767, "usd_sum": 0.004926 } }, { "task_id": "ogs:core:benchmark-task:pair-001", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "easy", "cuisine_region": "american", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "3fa6a67d5bfe7f1a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage option for the dish below from the candidates. Respond with just the candidate id (e.g. 'a').\n\nINPUT:\n{\n \"dish\": \"60-day dry-aged ribeye, medium-rare, served with peppercorn jus\",\n \"candidates\": {\n \"a\": \"young Barolo DOCG (high tannin, high acidity, full body)\",\n \"b\": \"off-dry German Kabinett Riesling\",\n \"c\": \"unoaked Muscadet sur lie\",\n \"d\": \"sweet Pedro Ximenez sherry\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "b", "d", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 378, "output_tokens": 1, "latency_ms": 649.1, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 378, "output_tokens": 1, "latency_ms": 614.4, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 378, "output_tokens": 1, "latency_ms": 662.9, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 378.0, "output_tokens_mean": 1.0, "latency_ms_mean": 642.133, "usd_sum": 0.002292 } }, { "task_id": "ogs:core:benchmark-task:pair-002", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "easy", "cuisine_region": "french", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "4b85899cd6206acb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish below from the candidates. Respond with just the candidate id.\n\nINPUT:\n{\n \"dish\": \"fresh Kumamoto oysters on the half shell, lemon and mignonette\",\n \"candidates\": {\n \"a\": \"oaked California Chardonnay (14.5% ABV, buttery)\",\n \"b\": \"Muscadet Sevre-et-Maine sur lie\",\n \"c\": \"Amarone della Valpolicella\",\n \"d\": \"bourbon old fashioned\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "b", "ranking": [ "b", "a", "d", "c" ] }, "samples": [ { "sample": 0, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 365, "output_tokens": 1, "latency_ms": 602.9, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 365, "output_tokens": 1, "latency_ms": 444.6, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 365, "output_tokens": 1, "latency_ms": 593.6, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 365.0, "output_tokens_mean": 1.0, "latency_ms_mean": 547.033, "usd_sum": 0.002214 } }, { "task_id": "ogs:core:benchmark-task:pair-003", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "mexican", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "41ed3ee840823502", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish below. Respond with just the candidate id.\n\nINPUT:\n{\n \"dish\": \"classic Chengdu-style mapo tofu (heavy doubanjiang, Sichuan peppercorn, ground pork, high chilli heat)\",\n \"candidates\": {\n \"a\": \"15% ABV Zinfandel\",\n \"b\": \"off-dry Riesling Kabinett (~10% ABV)\",\n \"c\": \"Islay single malt Scotch (Lagavulin 16)\",\n \"d\": \"Brunello di Montalcino Riserva\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "b", "ranking": [ "b", "d", "a", "c" ] }, "samples": [ { "sample": 0, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 378, "output_tokens": 1, "latency_ms": 561.5, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 378, "output_tokens": 1, "latency_ms": 565.7, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 378, "output_tokens": 1, "latency_ms": 865.5, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 378.0, "output_tokens_mean": 1.0, "latency_ms_mean": 664.233, "usd_sum": 0.002292 } }, { "task_id": "ogs:core:benchmark-task:pair-004", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "italian", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "82a4b41d0e3d5668", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish below. Respond with just the candidate id.\n\nINPUT:\n{\n \"dish\": \"warm goat cheese crouton on mesclun with walnut vinaigrette\",\n \"candidates\": {\n \"a\": \"Sancerre (Sauvignon Blanc, Loire)\",\n \"b\": \"Napa Cabernet Sauvignon Reserve\",\n \"c\": \"Vintage Port\",\n \"d\": \"lagered pilsner\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "d", "b", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 598.3, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 642.1, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 808.4, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 349.0, "output_tokens_mean": 1.0, "latency_ms_mean": 682.933, "usd_sum": 0.002118 } }, { "task_id": "ogs:core:benchmark-task:pair-005", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "441705237fe65e54", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish below. Respond with just the candidate id.\n\nINPUT:\n{\n \"dish\": \"warm dark chocolate fondant (70% cacao), molten centre, vanilla ice cream\",\n \"candidates\": {\n \"a\": \"dry Sancerre Sauvignon Blanc\",\n \"b\": \"vintage Port\",\n \"c\": \"bone-dry Brut Nature Champagne\",\n \"d\": \"Muscadet Sevre-et-Maine\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "b", "ranking": [ "b", "c", "a", "d" ] }, "samples": [ { "sample": 0, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 352, "output_tokens": 1, "latency_ms": 618.3, "usd": 0.000712, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 352, "output_tokens": 1, "latency_ms": 665.3, "usd": 0.000712, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 352, "output_tokens": 1, "latency_ms": 576.5, "usd": 0.000712, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 352.0, "output_tokens_mean": 1.0, "latency_ms_mean": 620.033, "usd_sum": 0.002136 } }, { "task_id": "ogs:core:benchmark-task:pair-006", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "b195ee1dfe7968ab", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage to pair across a premium edomae sushi omakase. Respond with just the candidate id.\n\nINPUT:\n{\n \"dish\": \"premium edomae sushi omakase (akami, toro, kohada, ikura, uni, anago)\",\n \"candidates\": {\n \"a\": \"Junmai Daiginjo sake (well-chilled)\",\n \"b\": \"heavily oaked California Chardonnay\",\n \"c\": \"Barolo Riserva\",\n \"d\": \"Islay single malt\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "b", "d", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 370, "output_tokens": 1, "latency_ms": 574.9, "usd": 0.000748, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 370, "output_tokens": 1, "latency_ms": 594.5, "usd": 0.000748, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 370, "output_tokens": 1, "latency_ms": 578.5, "usd": 0.000748, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 370.0, "output_tokens_mean": 1.0, "latency_ms_mean": 582.633, "usd_sum": 0.002244 } }, { "task_id": "ogs:core:benchmark-task:pair-007", "category": "pairing", "capability": "regional_pairing", "difficulty": "hard", "cuisine_region": "spanish", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "81bf14f26f4fa761", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for a classic paella valenciana (rabbit, chicken, garrofó beans, saffron). Respond with just the candidate id.\n\nINPUT:\n{\n \"dish\": \"authentic paella valenciana\",\n \"candidates\": {\n \"a\": \"young Rioja crianza (Tempranillo blend, light oak)\",\n \"b\": \"Amarone della Valpolicella Riserva\",\n \"c\": \"Islay peated single malt\",\n \"d\": \"off-dry Moscato d'Asti\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "b", "d", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 838.2, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 625.0, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 620.9, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 371.0, "output_tokens_mean": 1.0, "latency_ms_mean": 694.7, "usd_sum": 0.00225 } }, { "task_id": "ogs:core:benchmark-task:pair-008", "category": "pairing", "capability": "pairing_grade_reasoning", "difficulty": "hard", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.grade_scale" ], "prompt_template_hash": "51ad14586a063779", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n---\n\nA pairing's overall_score is computed as 68. Using the OGS grade scale, return the letter grade (ogs-match.md §5). Respond with just the grade token.\n\nINPUT:\n{\n \"overall_score\": 68\n}\n\nANSWER FORMAT: one_of:A+,A,B+,B,C+,C,D,F", "expected": { "value": "D" }, "samples": [ { "sample": 0, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 823.9, "usd": 0.000776, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 562.3, "usd": 0.000776, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 571.6, "usd": 0.000776, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 384.0, "output_tokens_mean": 1.0, "latency_ms_mean": 652.6, "usd_sum": 0.002328 } }, { "task_id": "ogs:core:benchmark-task:pair-009", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "easy", "cuisine_region": "italian", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "d7ade64ce48bfbe4", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish below from the candidates. Respond with just the candidate id (e.g. 'a').\n\nINPUT:\n{\n \"dish\": \"classic Neapolitan pizza Margherita (tomato, buffalo mozzarella, basil)\",\n \"candidates\": {\n \"a\": \"bright Chianti Classico (Sangiovese, high acid, medium tannin)\",\n \"b\": \"heavily oaked California Chardonnay\",\n \"c\": \"sweet ice wine\",\n \"d\": \"Islay peated whisky\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "b", "d", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 573.3, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 612.7, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 564.2, "usd": 0.00075, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 371.0, "output_tokens_mean": 1.0, "latency_ms_mean": 583.4, "usd_sum": 0.00225 } }, { "task_id": "ogs:core:benchmark-task:pair-010", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "chinese", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "637717fdf3577204", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish below.\n\nINPUT:\n{\n \"dish\": \"mapo tofu with doubanjiang and Sichuan peppercorn, medium-hot\",\n \"candidates\": {\n \"a\": \"off-dry German Riesling Spätlese\",\n \"b\": \"high-alcohol (15%) Zinfandel\",\n \"c\": \"bone-dry Fino sherry\",\n \"d\": \"straight rye whiskey\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "c", "d", "b" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 350, "output_tokens": 1, "latency_ms": 823.7, "usd": 0.000708, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 350, "output_tokens": 1, "latency_ms": 567.8, "usd": 0.000708, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 350, "output_tokens": 1, "latency_ms": 584.2, "usd": 0.000708, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 350.0, "output_tokens_mean": 1.0, "latency_ms_mean": 658.567, "usd_sum": 0.002124 } }, { "task_id": "ogs:core:benchmark-task:pair-011", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "indian", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "2b655f8b1ea64df8", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish below.\n\nINPUT:\n{\n \"dish\": \"butter chicken (murgh makhani) in rich tomato-cream sauce with fenugreek\",\n \"candidates\": {\n \"a\": \"off-dry Gewurztraminer\",\n \"b\": \"young tannic Cabernet Sauvignon\",\n \"c\": \"unoaked Muscadet\",\n \"d\": \"Islay single malt\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "c", "b", "d" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 346, "output_tokens": 1, "latency_ms": 904.2, "usd": 0.0007, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 346, "output_tokens": 1, "latency_ms": 1212.5, "usd": 0.0007, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 346, "output_tokens": 1, "latency_ms": 562.7, "usd": 0.0007, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 346.0, "output_tokens_mean": 1.0, "latency_ms_mean": 893.133, "usd_sum": 0.0021 } }, { "task_id": "ogs:core:benchmark-task:pair-012", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "ethiopian", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "3fe344c62017694c", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for the dish.\n\nINPUT:\n{\n \"dish\": \"doro wat: chicken stewed in berbere-spiced ghee, served with injera\",\n \"candidates\": {\n \"a\": \"juicy, low-tannin Beaujolais (Gamay) served slightly chilled\",\n \"b\": \"high-alcohol Amarone\",\n \"c\": \"bone-dry sparkling Prosecco Brut\",\n \"d\": \"heavily peated Islay whisky\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "c", "b", "d" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 361, "output_tokens": 1, "latency_ms": 625.4, "usd": 0.00073, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 361, "output_tokens": 1, "latency_ms": 623.3, "usd": 0.00073, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 361, "output_tokens": 1, "latency_ms": 621.0, "usd": 0.00073, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 361.0, "output_tokens_mean": 1.0, "latency_ms_mean": 623.233, "usd_sum": 0.00219 } }, { "task_id": "ogs:core:benchmark-task:pair-013", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "argentinian", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "4d30c6e439c9c85f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage.\n\nINPUT:\n{\n \"dish\": \"grilled ribeye over wood embers, served with chimichurri\",\n \"candidates\": {\n \"a\": \"old-vine Mendoza Malbec, medium-plus tannin, black fruit\",\n \"b\": \"unoaked Chablis\",\n \"c\": \"off-dry Moscato\",\n \"d\": \"dry Manzanilla sherry\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "d", "b", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 519.3, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 616.9, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 581.0, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 347.0, "output_tokens_mean": 1.0, "latency_ms_mean": 572.4, "usd_sum": 0.002106 } }, { "task_id": "ogs:core:benchmark-task:pair-014", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "848f37f91777acfb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for otoro nigiri topped with a brush of soy.\n\nINPUT:\n{\n \"dish\": \"bluefin tuna otoro nigiri, brushed soy\",\n \"candidates\": {\n \"a\": \"junmai daiginjo sake, chilled\",\n \"b\": \"young Chinon Cabernet Franc\",\n \"c\": \"dry Riesling Kabinett\",\n \"d\": \"sweet Sauternes\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "c", "b", "d" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 346, "output_tokens": 1, "latency_ms": 681.3, "usd": 0.0007, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 346, "output_tokens": 1, "latency_ms": 802.2, "usd": 0.0007, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 346, "output_tokens": 1, "latency_ms": 579.7, "usd": 0.0007, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 346.0, "output_tokens_mean": 1.0, "latency_ms_mean": 687.733, "usd_sum": 0.0021 } }, { "task_id": "ogs:core:benchmark-task:pair-015", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "hard", "cuisine_region": "moroccan", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "f5ecf9dcd59f0d0a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage.\n\nINPUT:\n{\n \"dish\": \"slow-cooked lamb shoulder tagine with preserved lemon and green olives\",\n \"candidates\": {\n \"a\": \"Southern Rhône Grenache-Syrah blend (Gigondas), moderate tannin\",\n \"b\": \"unoaked Muscadet\",\n \"c\": \"Champagne Blanc de Blancs\",\n \"d\": \"young high-tannin Barolo\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "d", "c", "b" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 3548.2, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 569.8, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 580.5, "usd": 0.000702, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 347.0, "output_tokens_mean": 1.0, "latency_ms_mean": 1566.167, "usd_sum": 0.002106 } }, { "task_id": "ogs:core:benchmark-task:pair-016", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "vietnamese", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "3dd7c0170877ac9b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for a bowl of Vietnamese beef pho.\n\nINPUT:\n{\n \"dish\": \"pho bo: beef broth with star anise, cinnamon, rice noodles, rare beef, basil, lime\",\n \"candidates\": {\n \"a\": \"cold Vietnamese lager-style beer (e.g. Saigon or 333)\",\n \"b\": \"tannic Cabernet Sauvignon\",\n \"c\": \"heavily oaked Chardonnay\",\n \"d\": \"sweet Tokaji Aszú 5 puttonyos\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "b", "c", "d" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 366, "output_tokens": 1, "latency_ms": 572.3, "usd": 0.00074, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 366, "output_tokens": 1, "latency_ms": 590.4, "usd": 0.00074, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 366, "output_tokens": 1, "latency_ms": 478.7, "usd": 0.00074, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 366.0, "output_tokens_mean": 1.0, "latency_ms_mean": 547.133, "usd_sum": 0.00222 } }, { "task_id": "ogs:core:benchmark-task:pair-017", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "hard", "cuisine_region": "french", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "8f60336584f33baf", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for 24-month aged Comté served on its own.\n\nINPUT:\n{\n \"dish\": \"24-month aged Comté, served at room temperature\",\n \"candidates\": {\n \"a\": \"Jura Vin Jaune (Savagnin, oxidative, nutty)\",\n \"b\": \"young oaky Cabernet Sauvignon\",\n \"c\": \"dry Muscadet\",\n \"d\": \"Sauternes\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "d", "b", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 551.5, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 604.0, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 2111.6, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 349.0, "output_tokens_mean": 1.0, "latency_ms_mean": 1089.033, "usd_sum": 0.002118 } }, { "task_id": "ogs:core:benchmark-task:pair-018", "category": "pairing", "capability": "regional_pairing", "difficulty": "medium", "cuisine_region": "thai", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "9209873bc05779b7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for a fragrant, moderately spicy Thai green curry with chicken and Thai basil.\n\nINPUT:\n{\n \"dish\": \"Thai green curry with chicken, Thai basil, kaffir lime\",\n \"candidates\": {\n \"a\": \"off-dry New Zealand Sauvignon Blanc with residual sugar\",\n \"b\": \"heavy Port wine\",\n \"c\": \"young tannic Bordeaux\",\n \"d\": \"Islay peated whisky\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "c", "b", "d" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 350, "output_tokens": 1, "latency_ms": 674.0, "usd": 0.000708, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 350, "output_tokens": 1, "latency_ms": 1122.9, "usd": 0.000708, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 350, "output_tokens": 1, "latency_ms": 636.1, "usd": 0.000708, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 350.0, "output_tokens_mean": 1.0, "latency_ms_mean": 811.0, "usd_sum": 0.002124 } }, { "task_id": "ogs:core:benchmark-task:pair-019", "category": "pairing", "capability": "best_beverage_selection", "difficulty": "medium", "cuisine_region": "mexican", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "da735293a9d3102b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage.\n\nINPUT:\n{\n \"dish\": \"Oaxacan mole negro enchiladas (rich chocolate-chile-spice sauce over chicken)\",\n \"candidates\": {\n \"a\": \"medium-tannin Garnacha from Aragón\",\n \"b\": \"unoaked Muscadet\",\n \"c\": \"very sweet late-harvest Riesling\",\n \"d\": \"bone-dry Brut Champagne\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "d", "c", "b" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 345, "output_tokens": 1, "latency_ms": 550.3, "usd": 0.000698, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 345, "output_tokens": 1, "latency_ms": 948.3, "usd": 0.000698, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 345, "output_tokens": 1, "latency_ms": 595.5, "usd": 0.000698, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 345.0, "output_tokens_mean": 1.0, "latency_ms_mean": 698.033, "usd_sum": 0.002094 } }, { "task_id": "ogs:core:benchmark-task:pair-020", "category": "pairing", "capability": "pairing_grade_reasoning", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.grade_scale" ], "prompt_template_hash": "bac251ebb1c064ef", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n---\n\nA pairing's overall_score is computed as 96. Using the OGS grade scale, return the letter grade.\n\nINPUT:\n{\n \"overall_score\": 96\n}\n\nANSWER FORMAT: one_of:A+,A,B+,B,C+,C,D,F", "expected": { "value": "A+" }, "samples": [ { "sample": 0, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 371, "output_tokens": 2, "latency_ms": 597.3, "usd": 0.000758, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 371, "output_tokens": 2, "latency_ms": 800.8, "usd": 0.000758, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 371, "output_tokens": 2, "latency_ms": 599.6, "usd": 0.000758, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 371.0, "output_tokens_mean": 2.0, "latency_ms_mean": 665.9, "usd_sum": 0.002274 } }, { "task_id": "ogs:core:benchmark-task:region-001", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "easy", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "1df867dd3a55af5b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhat is the ONLY grape variety permitted in Barolo DOCG? Respond with just the variety name.\n\nANSWER FORMAT: string", "expected": { "value": "nebbiolo" }, "samples": [ { "sample": 0, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 246, "output_tokens": 3, "latency_ms": 676.3, "usd": 0.000516, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 246, "output_tokens": 3, "latency_ms": 617.2, "usd": 0.000516, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 246, "output_tokens": 3, "latency_ms": 550.1, "usd": 0.000516, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 246.0, "output_tokens_mean": 3.0, "latency_ms_mean": 614.533, "usd_sum": 0.001548 } }, { "task_id": "ogs:core:benchmark-task:region-002", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "easy", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "24a95f8a1c0a0a45", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhat single grape variety is used for Chablis AOC? Respond with just the variety name.\n\nANSWER FORMAT: string", "expected": { "value": "chardonnay" }, "samples": [ { "sample": 0, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 246, "output_tokens": 2, "latency_ms": 747.9, "usd": 0.000508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 246, "output_tokens": 2, "latency_ms": 617.0, "usd": 0.000508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 246, "output_tokens": 2, "latency_ms": 628.4, "usd": 0.000508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 246.0, "output_tokens_mean": 2.0, "latency_ms_mean": 664.433, "usd_sum": 0.001524 } }, { "task_id": "ogs:core:benchmark-task:region-003", "category": "regional", "capability": "dish_origin", "difficulty": "easy", "cuisine_region": "vietnamese", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "15d36148f8b853e6", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhich country is phở originally from? Respond with just the country name.\n\nANSWER FORMAT: string", "expected": { "value": "vietnam" }, "samples": [ { "sample": 0, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 241, "output_tokens": 1, "latency_ms": 561.8, "usd": 0.00049, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 241, "output_tokens": 1, "latency_ms": 621.7, "usd": 0.00049, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 241, "output_tokens": 1, "latency_ms": 465.4, "usd": 0.00049, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 241.0, "output_tokens_mean": 1.0, "latency_ms_mean": 549.633, "usd_sum": 0.00147 } }, { "task_id": "ogs:core:benchmark-task:region-004", "category": "regional", "capability": "classic_regional_pairing", "difficulty": "hard", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "e332af036a2bd591", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nName the classic Alsace wine traditionally paired with ripe, stinky Muenster cheese. One word, grape variety only.\n\nANSWER FORMAT: string", "expected": { "value": "gewurztraminer" }, "samples": [ { "sample": 0, "raw_response": "Gewurztraminer", "compliant": true, "score": 1.0, "detail": { "predicted": "gewurztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 251, "output_tokens": 4, "latency_ms": 848.3, "usd": 0.000534, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Gewurztraminer", "compliant": true, "score": 1.0, "detail": { "predicted": "gewurztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 251, "output_tokens": 4, "latency_ms": 727.8, "usd": 0.000534, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Gewurztraminer", "compliant": true, "score": 1.0, "detail": { "predicted": "gewurztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 251, "output_tokens": 4, "latency_ms": 620.8, "usd": 0.000534, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 251.0, "output_tokens_mean": 4.0, "latency_ms_mean": 732.3, "usd_sum": 0.001602 } }, { "task_id": "ogs:core:benchmark-task:region-005", "category": "regional", "capability": "french_classical_cuisine", "difficulty": "medium", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "4aa2c63ffdeeacfb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nName the French mother sauce that is made from a brown roux, brown stock and mirepoix, traditionally enriched with tomato. One word, lowercase.\n\nANSWER FORMAT: string", "expected": { "value": "espagnole" }, "samples": [ { "sample": 0, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 3, "latency_ms": 582.4, "usd": 0.000538, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 3, "latency_ms": 618.6, "usd": 0.000538, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 3, "latency_ms": 599.8, "usd": 0.000538, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 257.0, "output_tokens_mean": 3.0, "latency_ms_mean": 600.267, "usd_sum": 0.001614 } }, { "task_id": "ogs:core:benchmark-task:region-006", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "medium", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "979e7579b34d9797", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhat is the name of the official Rioja classification for a red wine aged at least 2 years (1 in oak) and 3+ years total? Respond with just the term.\n\nINPUT:\n{\n \"question\": \"official Rioja classification for red wine aged 2+ years (1+ in oak), 3+ total\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "reserva" }, "samples": [ { "sample": 0, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 295, "output_tokens": 1, "latency_ms": 1566.6, "usd": 0.000598, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 295, "output_tokens": 1, "latency_ms": 595.5, "usd": 0.000598, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 295, "output_tokens": 1, "latency_ms": 635.9, "usd": 0.000598, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 295.0, "output_tokens_mean": 1.0, "latency_ms_mean": 932.667, "usd_sum": 0.001794 } }, { "task_id": "ogs:core:benchmark-task:region-007", "category": "regional", "capability": "dish_origin", "difficulty": "easy", "cuisine_region": "korean", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "23a69016b1082553", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nFrom which country does kimchi originate? Respond with just the country name in English.\n\nINPUT:\n{\n \"dish\": \"kimchi\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "korea", "aliases": [ "south korea", "republic of korea" ] }, "samples": [ { "sample": 0, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 256, "output_tokens": 2, "latency_ms": 601.5, "usd": 0.000528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 256, "output_tokens": 2, "latency_ms": 577.1, "usd": 0.000528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 256, "output_tokens": 2, "latency_ms": 595.1, "usd": 0.000528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 256.0, "output_tokens_mean": 2.0, "latency_ms_mean": 591.233, "usd_sum": 0.001584 } }, { "task_id": "ogs:core:benchmark-task:region-008", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "hard", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "0a12eb057eb17654", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhat is the single grape variety required for Barbaresco DOCG?\n\nINPUT:\n{\n \"wine\": \"Barbaresco DOCG\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "nebbiolo" }, "samples": [ { "sample": 0, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 3, "latency_ms": 532.3, "usd": 0.000536, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 3, "latency_ms": 648.5, "usd": 0.000536, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 3, "latency_ms": 600.9, "usd": 0.000536, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 256.0, "output_tokens_mean": 3.0, "latency_ms_mean": 593.9, "usd_sum": 0.001608 } }, { "task_id": "ogs:core:benchmark-task:region-009", "category": "regional", "capability": "dish_origin", "difficulty": "medium", "cuisine_region": "peruvian", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "767d178c3cce3333", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhich country is classic ceviche most commonly attributed to? Respond with the country name.\n\nINPUT:\n{\n \"dish\": \"ceviche\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "peru" }, "samples": [ { "sample": 0, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 2, "latency_ms": 1122.1, "usd": 0.000528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 2, "latency_ms": 685.7, "usd": 0.000528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 2, "latency_ms": 549.1, "usd": 0.000528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 256.0, "output_tokens_mean": 2.0, "latency_ms_mean": 785.633, "usd_sum": 0.001584 } }, { "task_id": "ogs:core:benchmark-task:region-010", "category": "regional", "capability": "dish_origin", "difficulty": "easy", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "1001169bc92aaacd", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nIn which country does paella valenciana originate? Respond with the country name.\n\nINPUT:\n{\n \"dish\": \"paella valenciana\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "spain" }, "samples": [ { "sample": 0, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 1, "latency_ms": 700.1, "usd": 0.000522, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 1, "latency_ms": 541.3, "usd": 0.000522, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 1, "latency_ms": 565.6, "usd": 0.000522, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 257.0, "output_tokens_mean": 1.0, "latency_ms_mean": 602.333, "usd_sum": 0.001566 } }, { "task_id": "ogs:core:benchmark-task:region-011", "category": "regional", "capability": "classic_regional_pairing", "difficulty": "medium", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "571e5074e66e6a11", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nName the classic French white wine region traditionally paired with raw oysters. Respond with just the region name.\n\nINPUT:\n{\n \"dish\": \"raw oysters on the half shell\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "chablis", "aliases": [ "muscadet" ] }, "samples": [ { "sample": 0, "raw_response": "Muscadet", "compliant": true, "score": 1.0, "detail": { "predicted": "muscadet", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 263, "output_tokens": 3, "latency_ms": 784.8, "usd": 0.00055, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Muscadet", "compliant": true, "score": 1.0, "detail": { "predicted": "muscadet", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 263, "output_tokens": 3, "latency_ms": 567.5, "usd": 0.00055, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Muscadet", "compliant": true, "score": 1.0, "detail": { "predicted": "muscadet", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 263, "output_tokens": 3, "latency_ms": 537.4, "usd": 0.00055, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 263.0, "output_tokens_mean": 3.0, "latency_ms_mean": 629.9, "usd_sum": 0.00165 } }, { "task_id": "ogs:core:benchmark-task:region-012", "category": "regional", "capability": "french_classical_cuisine", "difficulty": "medium", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "d9792be4d5ca7335", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nName the French mother sauce made from clarified butter, egg yolks, and lemon juice.\n\nINPUT:\n{\n \"description\": \"emulsion of clarified butter, egg yolks, and lemon juice\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "hollandaise" }, "samples": [ { "sample": 0, "raw_response": "hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 268, "output_tokens": 4, "latency_ms": 607.8, "usd": 0.000568, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 268, "output_tokens": 4, "latency_ms": 681.0, "usd": 0.000568, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 268, "output_tokens": 4, "latency_ms": 607.0, "usd": 0.000568, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 268.0, "output_tokens_mean": 4.0, "latency_ms_mean": 631.933, "usd_sum": 0.001704 } }, { "task_id": "ogs:core:benchmark-task:region-013", "category": "regional", "capability": "dish_origin", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "c831a091be5025f9", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nIn which country did edomae-style sushi originate?\n\nINPUT:\n{\n \"dish\": \"edomae sushi\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "japan" }, "samples": [ { "sample": 0, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 252, "output_tokens": 1, "latency_ms": 632.9, "usd": 0.000512, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 252, "output_tokens": 1, "latency_ms": 574.7, "usd": 0.000512, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 252, "output_tokens": 1, "latency_ms": 692.1, "usd": 0.000512, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 252.0, "output_tokens_mean": 1.0, "latency_ms_mean": 633.233, "usd_sum": 0.001536 } }, { "task_id": "ogs:core:benchmark-task:region-014", "category": "regional", "capability": "dish_origin", "difficulty": "medium", "cuisine_region": "moroccan", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "7d761cbfb86342af", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nIn which country does the slow-cooked dish tagine originate?\n\nINPUT:\n{\n \"dish\": \"tagine (clay-pot slow-cooked stew)\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "morocco" }, "samples": [ { "sample": 0, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 260, "output_tokens": 2, "latency_ms": 559.1, "usd": 0.000536, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 260, "output_tokens": 2, "latency_ms": 601.8, "usd": 0.000536, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 260, "output_tokens": 2, "latency_ms": 561.2, "usd": 0.000536, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 260.0, "output_tokens_mean": 2.0, "latency_ms_mean": 574.033, "usd_sum": 0.001608 } }, { "task_id": "ogs:core:benchmark-task:region-015", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "hard", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "2f35d24bb9d58118", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhat single grape variety is used for white Sancerre AOC?\n\nINPUT:\n{\n \"wine\": \"Sancerre AOC blanc\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "samples": [ { "sample": 0, "raw_response": "Sauvignon", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 257, "output_tokens": 3, "latency_ms": 575.3, "usd": 0.000538, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Sauvignon_blanc", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon_blanc", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 257, "output_tokens": 5, "latency_ms": 622.4, "usd": 0.000554, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Sauvignon_blanc", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon_blanc", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 257, "output_tokens": 5, "latency_ms": 623.8, "usd": 0.000554, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 257.0, "output_tokens_mean": 4.333, "latency_ms_mean": 607.167, "usd_sum": 0.001646 } }, { "task_id": "ogs:core:benchmark-task:region-016", "category": "regional", "capability": "dish_origin", "difficulty": "easy", "cuisine_region": "mexican", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "efb489c56faf463a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nIn which country does mole poblano originate?\n\nINPUT:\n{\n \"dish\": \"mole poblano\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "mexico" }, "samples": [ { "sample": 0, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 250, "output_tokens": 1, "latency_ms": 1353.5, "usd": 0.000508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 250, "output_tokens": 1, "latency_ms": 644.0, "usd": 0.000508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 250, "output_tokens": 1, "latency_ms": 940.0, "usd": 0.000508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 250.0, "output_tokens_mean": 1.0, "latency_ms_mean": 979.167, "usd_sum": 0.001524 } }, { "task_id": "ogs:core:benchmark-task:region-017", "category": "regional", "capability": "classic_regional_pairing", "difficulty": "medium", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "53530e4634162afc", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nName the Alsatian white wine traditionally served with choucroute garnie.\n\nINPUT:\n{\n \"dish\": \"choucroute garnie\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "riesling" }, "samples": [ { "sample": 0, "raw_response": "Riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 3, "latency_ms": 599.6, "usd": 0.000538, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 2, "latency_ms": 524.9, "usd": 0.00053, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 257, "output_tokens": 3, "latency_ms": 597.6, "usd": 0.000538, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 257.0, "output_tokens_mean": 2.667, "latency_ms_mean": 574.033, "usd_sum": 0.001606 } }, { "task_id": "ogs:core:benchmark-task:region-018", "category": "regional", "capability": "dish_origin", "difficulty": "medium", "cuisine_region": "brazilian", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "28a636bdc82633de", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhich country claims feijoada completa as a national dish?\n\nINPUT:\n{\n \"dish\": \"feijoada completa\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "brazil" }, "samples": [ { "sample": 0, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 253, "output_tokens": 1, "latency_ms": 565.3, "usd": 0.000514, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 253, "output_tokens": 1, "latency_ms": 641.3, "usd": 0.000514, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 253, "output_tokens": 1, "latency_ms": 570.4, "usd": 0.000514, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 253.0, "output_tokens_mean": 1.0, "latency_ms_mean": 592.333, "usd_sum": 0.001542 } }, { "task_id": "ogs:core:benchmark-task:region-019", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "hard", "cuisine_region": "hungarian", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "2c5869ce479f65cc", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nTokaji Aszú's vineyards are centred in a single country. Name that country in English.\n\nINPUT:\n{\n \"wine\": \"Tokaji Aszú\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "hungary" }, "samples": [ { "sample": 0, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 262, "output_tokens": 2, "latency_ms": 637.4, "usd": 0.00054, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 262, "output_tokens": 2, "latency_ms": 756.9, "usd": 0.00054, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 262, "output_tokens": 2, "latency_ms": 524.9, "usd": 0.00054, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 262.0, "output_tokens_mean": 2.0, "latency_ms_mean": 639.733, "usd_sum": 0.00162 } }, { "task_id": "ogs:core:benchmark-task:region-020", "category": "regional", "capability": "classic_regional_pairing", "difficulty": "hard", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "aa3761bdbf2d490e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nName the Galician white wine grape traditionally paired with pulpo á feira (boiled octopus with pimentón).\n\nINPUT:\n{\n \"dish\": \"pulpo á feira — Galician boiled octopus with pimentón and olive oil\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "albarino", "aliases": [ "albariño" ] }, "samples": [ { "sample": 0, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 278, "output_tokens": 3, "latency_ms": 558.6, "usd": 0.00058, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 278, "output_tokens": 3, "latency_ms": 900.3, "usd": 0.00058, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 278, "output_tokens": 3, "latency_ms": 557.2, "usd": 0.00058, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 278.0, "output_tokens_mean": 3.0, "latency_ms_mean": 672.033, "usd_sum": 0.00174 } }, { "task_id": "ogs:core:benchmark-task:risk-001", "category": "risk", "capability": "risk_identification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "08845fcf7f8beb09", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"salmon and tuna nigiri\",\n \"beverage\": \"young Bordeaux Left Bank (Cabernet Sauvignon, high tannin)\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_TANNIN_FISH" }, "samples": [ { "sample": 0, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_TANNIN_FISH", "expected": "RISK_TANNIN_FISH", "aliases": [] }, "metrics": { "input_tokens": 637, "output_tokens": 7, "latency_ms": 726.5, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_TANNIN_FISH", "expected": "RISK_TANNIN_FISH", "aliases": [] }, "metrics": { "input_tokens": 637, "output_tokens": 7, "latency_ms": 613.5, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_TANNIN_FISH", "expected": "RISK_TANNIN_FISH", "aliases": [] }, "metrics": { "input_tokens": 637, "output_tokens": 7, "latency_ms": 580.9, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 637.0, "output_tokens_mean": 7.0, "latency_ms_mean": 640.3, "usd_sum": 0.00399 } }, { "task_id": "ogs:core:benchmark-task:risk-002", "category": "risk", "capability": "risk_identification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "7a188b424515258f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"Thai green curry with bird's eye chilli, high heat\",\n \"beverage\": \"15.5% ABV California Zinfandel\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SPICE_ALCOHOL" }, "samples": [ { "sample": 0, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_SPICE_ALCOHOL", "expected": "RISK_SPICE_ALCOHOL", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 7, "latency_ms": 627.5, "usd": 0.001334, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_SPICE_ALCOHOL", "expected": "RISK_SPICE_ALCOHOL", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 7, "latency_ms": 629.4, "usd": 0.001334, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_SPICE_ALCOHOL", "expected": "RISK_SPICE_ALCOHOL", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 7, "latency_ms": 596.7, "usd": 0.001334, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 639.0, "output_tokens_mean": 7.0, "latency_ms_mean": 617.867, "usd_sum": 0.004002 } }, { "task_id": "ogs:core:benchmark-task:risk-003", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "a60fa6dd5c1ff452", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code for the pairing. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"delicate flounder sashimi with ponzu\",\n \"beverage\": \"heavily new-oaked California Chardonnay, 14% ABV, buttery ML\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_OAK_MASKS" }, "samples": [ { "sample": 0, "raw_response": "RISK_OAK_MASKS", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_OAK_MASKS", "expected": "RISK_OAK_MASKS", "aliases": [] }, "metrics": { "input_tokens": 642, "output_tokens": 6, "latency_ms": 636.4, "usd": 0.001332, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_OAK_MASKS", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_OAK_MASKS", "expected": "RISK_OAK_MASKS", "aliases": [] }, "metrics": { "input_tokens": 642, "output_tokens": 6, "latency_ms": 679.7, "usd": 0.001332, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_OAK_MASKS", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_OAK_MASKS", "expected": "RISK_OAK_MASKS", "aliases": [] }, "metrics": { "input_tokens": 642, "output_tokens": 6, "latency_ms": 708.7, "usd": 0.001332, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 642.0, "output_tokens_mean": 6.0, "latency_ms_mean": 674.933, "usd_sum": 0.003996 } }, { "task_id": "ogs:core:benchmark-task:risk-004", "category": "risk", "capability": "risk_severity", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "16286de7fea14ae1", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nUsing OGS risk severity levels (low/medium/high), classify the RISK_ALCOHOL_OVERPOWERS severity for the pairing below. Respond with just the severity token.\n\nINPUT:\n{\n \"dish\": \"pan-seared halibut with beurre blanc, very delicate flavours\",\n \"beverage\": \"15.5% ABV Amarone della Valpolicella\"\n}\n\nANSWER FORMAT: one_of:low,medium,high", "expected": { "value": "high" }, "samples": [ { "sample": 0, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 604, "output_tokens": 1, "latency_ms": 556.2, "usd": 0.001216, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 604, "output_tokens": 1, "latency_ms": 586.7, "usd": 0.001216, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 604, "output_tokens": 1, "latency_ms": 593.3, "usd": 0.001216, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 604.0, "output_tokens_mean": 1.0, "latency_ms_mean": 578.733, "usd_sum": 0.003648 } }, { "task_id": "ogs:core:benchmark-task:risk-005", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "cd44f8ac361108e8", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code for the pairing. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"caramel panna cotta with honey\",\n \"beverage\": \"bone-dry Brut Nature Champagne (zero dosage)\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SWEETNESS_CONFLICT" }, "samples": [ { "sample": 0, "raw_response": "RISK_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_SWEETNESS_CONFLICT", "expected": "RISK_SWEETNESS_CONFLICT", "aliases": [] }, "metrics": { "input_tokens": 631, "output_tokens": 8, "latency_ms": 626.7, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_SWEETNESS_CONFLICT", "expected": "RISK_SWEETNESS_CONFLICT", "aliases": [] }, "metrics": { "input_tokens": 631, "output_tokens": 8, "latency_ms": 467.8, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "RISK_SWEETNESS_CONFLICT", "expected": "RISK_SWEETNESS_CONFLICT", "aliases": [] }, "metrics": { "input_tokens": 631, "output_tokens": 8, "latency_ms": 598.9, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 631.0, "output_tokens_mean": 8.0, "latency_ms_mean": 564.467, "usd_sum": 0.003978 } }, { "task_id": "ogs:core:benchmark-task:risk-006", "category": "risk", "capability": "risk_identification", "difficulty": "easy", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "28cb271326a709c7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"raw tuna sashimi with a light soy-wasabi dip\",\n \"beverage\": \"young tannic Napa Cabernet Sauvignon\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_TANNIN_FISH" }, "samples": [ { "sample": 0, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_tannin_fish", "aliases": [] }, "metrics": { "input_tokens": 637, "output_tokens": 7, "latency_ms": 557.4, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_tannin_fish", "aliases": [] }, "metrics": { "input_tokens": 637, "output_tokens": 7, "latency_ms": 785.6, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_tannin_fish", "aliases": [] }, "metrics": { "input_tokens": 637, "output_tokens": 7, "latency_ms": 1134.5, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 637.0, "output_tokens_mean": 7.0, "latency_ms_mean": 825.833, "usd_sum": 0.00399 } }, { "task_id": "ogs:core:benchmark-task:risk-007", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "thai", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "93c46eac23eca249", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"spicy Thai green curry with chilies and coconut milk\",\n \"beverage\": \"15.5% abv California Zinfandel\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SPICE_ALCOHOL" }, "samples": [ { "sample": 0, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_spice_alcohol", "expected": "risk_spice_alcohol", "aliases": [] }, "metrics": { "input_tokens": 640, "output_tokens": 7, "latency_ms": 596.7, "usd": 0.001336, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_spice_alcohol", "expected": "risk_spice_alcohol", "aliases": [] }, "metrics": { "input_tokens": 640, "output_tokens": 7, "latency_ms": 618.3, "usd": 0.001336, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_spice_alcohol", "expected": "risk_spice_alcohol", "aliases": [] }, "metrics": { "input_tokens": 640, "output_tokens": 7, "latency_ms": 590.2, "usd": 0.001336, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 640.0, "output_tokens_mean": 7.0, "latency_ms_mean": 601.733, "usd_sum": 0.004008 } }, { "task_id": "ogs:core:benchmark-task:risk-008", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "2409e606629eebf9", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"grilled escarole salad with bitter radicchio and walnuts\",\n \"beverage\": \"bone-dry bitter amontillado sherry\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_BITTER_AMPLIFY" }, "samples": [ { "sample": 0, "raw_response": "RISK_BITTER_AMPLIFY", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_bitter_amplify", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 642, "output_tokens": 7, "latency_ms": 588.8, "usd": 0.00134, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_BITTER_AMPLIFY", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_bitter_amplify", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 642, "output_tokens": 7, "latency_ms": 584.0, "usd": 0.00134, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_BITTER_AMPLIFY", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_bitter_amplify", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 642, "output_tokens": 7, "latency_ms": 583.2, "usd": 0.00134, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 642.0, "output_tokens_mean": 7.0, "latency_ms_mean": 585.333, "usd_sum": 0.00402 } }, { "task_id": "ogs:core:benchmark-task:risk-009", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "a00498fd7fce7cb7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"raw scallop crudo with yuzu\",\n \"beverage\": \"heavily oaked California Chardonnay, new French barrels\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_OAK_MASKS" }, "samples": [ { "sample": 0, "raw_response": "RISK_OAK_MASKS", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_oak_masks", "expected": "risk_oak_masks", "aliases": [] }, "metrics": { "input_tokens": 638, "output_tokens": 6, "latency_ms": 752.2, "usd": 0.001324, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_OAK_MASKS", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_oak_masks", "expected": "risk_oak_masks", "aliases": [] }, "metrics": { "input_tokens": 638, "output_tokens": 6, "latency_ms": 824.3, "usd": 0.001324, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_OAK_MASKS", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_oak_masks", "expected": "risk_oak_masks", "aliases": [] }, "metrics": { "input_tokens": 638, "output_tokens": 6, "latency_ms": 568.4, "usd": 0.001324, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 638.0, "output_tokens_mean": 6.0, "latency_ms_mean": 714.967, "usd_sum": 0.003972 } }, { "task_id": "ogs:core:benchmark-task:risk-010", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "b28af5fc40407ce0", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"warm clear beef consommé\",\n \"beverage\": \"sweet late-harvest Moscato d'Asti\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SWEETNESS_CONFLICT" }, "samples": [ { "sample": 0, "raw_response": "RISK_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_sweetness_conflict", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 8, "latency_ms": 595.5, "usd": 0.001332, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_sweetness_conflict", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 8, "latency_ms": 613.0, "usd": 0.001332, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_sweetness_conflict", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 8, "latency_ms": 586.1, "usd": 0.001332, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 634.0, "output_tokens_mean": 8.0, "latency_ms_mean": 598.2, "usd_sum": 0.003996 } }, { "task_id": "ogs:core:benchmark-task:risk-011", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "fba6f85afa81595f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"frisée salad with aggressive Dijon vinaigrette (1:2 vinegar to oil)\",\n \"beverage\": \"bone-dry Brut Nature Champagne\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_ACID_CLASH" }, "samples": [ { "sample": 0, "raw_response": "RISK_ACID_CLASH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_acid_clash", "expected": "risk_acid_clash", "aliases": [] }, "metrics": { "input_tokens": 641, "output_tokens": 6, "latency_ms": 578.9, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_ACID_CLASH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_acid_clash", "expected": "risk_acid_clash", "aliases": [] }, "metrics": { "input_tokens": 641, "output_tokens": 6, "latency_ms": 629.9, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_ACID_CLASH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_acid_clash", "expected": "risk_acid_clash", "aliases": [] }, "metrics": { "input_tokens": 641, "output_tokens": 6, "latency_ms": 765.9, "usd": 0.00133, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 641.0, "output_tokens_mean": 6.0, "latency_ms_mean": 658.233, "usd_sum": 0.00399 } }, { "task_id": "ogs:core:benchmark-task:risk-012", "category": "risk", "capability": "risk_identification", "difficulty": "easy", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "2f3a4360a39afdc9", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"steamed turbot with beurre blanc\",\n \"beverage\": \"young powerful Barolo\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_INTENSITY_MISMATCH" }, "samples": [ { "sample": 0, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_intensity_mismatch", "aliases": [] }, "metrics": { "input_tokens": 630, "output_tokens": 7, "latency_ms": 762.4, "usd": 0.001316, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_intensity_mismatch", "aliases": [] }, "metrics": { "input_tokens": 630, "output_tokens": 7, "latency_ms": 614.6, "usd": 0.001316, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_intensity_mismatch", "aliases": [] }, "metrics": { "input_tokens": 630, "output_tokens": 7, "latency_ms": 582.6, "usd": 0.001316, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 630.0, "output_tokens_mean": 7.0, "latency_ms_mean": 653.2, "usd_sum": 0.003948 } }, { "task_id": "ogs:core:benchmark-task:risk-013", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "390e90cae060ada8", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"yellowtail sashimi\",\n \"beverage\": \"overproof 63% abv Jamaican rum\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_ALCOHOL_OVERPOWERS" }, "samples": [ { "sample": 0, "raw_response": "RISK_ALCOHOL_OVERPOWERS", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_alcohol_overpowers", "expected": "risk_alcohol_overpowers", "aliases": [] }, "metrics": { "input_tokens": 632, "output_tokens": 9, "latency_ms": 647.4, "usd": 0.001336, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_ALCOHOL_OVERPOWERS", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_alcohol_overpowers", "expected": "risk_alcohol_overpowers", "aliases": [] }, "metrics": { "input_tokens": 632, "output_tokens": 9, "latency_ms": 1906.1, "usd": 0.001336, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_ALCOHOL_OVERPOWERS", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_alcohol_overpowers", "expected": "risk_alcohol_overpowers", "aliases": [] }, "metrics": { "input_tokens": 632, "output_tokens": 9, "latency_ms": 707.0, "usd": 0.001336, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 632.0, "output_tokens_mean": 9.0, "latency_ms_mean": 1086.833, "usd_sum": 0.004008 } }, { "task_id": "ogs:core:benchmark-task:risk-014", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "d83b8b2ecabe9907", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"gin-cured salmon gravlax with dill\",\n \"beverage\": \"young tannic Chianti Classico\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_TANNIN_FISH" }, "samples": [ { "sample": 0, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_tannin_fish", "aliases": [] }, "metrics": { "input_tokens": 635, "output_tokens": 7, "latency_ms": 685.7, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_tannin_fish", "aliases": [] }, "metrics": { "input_tokens": 635, "output_tokens": 7, "latency_ms": 666.1, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_TANNIN_FISH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_tannin_fish", "expected": "risk_tannin_fish", "aliases": [] }, "metrics": { "input_tokens": 635, "output_tokens": 7, "latency_ms": 650.0, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 635.0, "output_tokens_mean": 7.0, "latency_ms_mean": 667.267, "usd_sum": 0.003978 } }, { "task_id": "ogs:core:benchmark-task:risk-015", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "1e83097d483e0639", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"poached lobster with drawn butter\",\n \"beverage\": \"aggressive 80-IBU West Coast IPA\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_BITTER_AMPLIFY" }, "samples": [ { "sample": 0, "raw_response": "RISK_BITTER_AMPLIFY", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_bitter_amplify", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 635, "output_tokens": 7, "latency_ms": 677.7, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_BITTER_AMPLIFY", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_bitter_amplify", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 635, "output_tokens": 7, "latency_ms": 611.7, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_BITTER_AMPLIFY", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_bitter_amplify", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 635, "output_tokens": 7, "latency_ms": 775.2, "usd": 0.001326, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 635.0, "output_tokens_mean": 7.0, "latency_ms_mean": 688.2, "usd_sum": 0.003978 } }, { "task_id": "ogs:core:benchmark-task:risk-016", "category": "risk", "capability": "risk_identification", "difficulty": "easy", "cuisine_region": "mexican", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "b2e02272ca87b2d4", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"habanero-heavy Yucatán salsa\",\n \"beverage\": \"15% abv Zinfandel\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SPICE_ALCOHOL" }, "samples": [ { "sample": 0, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_spice_alcohol", "expected": "risk_spice_alcohol", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 7, "latency_ms": 692.0, "usd": 0.001324, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_spice_alcohol", "expected": "risk_spice_alcohol", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 7, "latency_ms": 781.6, "usd": 0.001324, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_SPICE_ALCOHOL", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_spice_alcohol", "expected": "risk_spice_alcohol", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 7, "latency_ms": 1029.9, "usd": 0.001324, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 634.0, "output_tokens_mean": 7.0, "latency_ms_mean": 834.5, "usd_sum": 0.003972 } }, { "task_id": "ogs:core:benchmark-task:risk-017", "category": "risk", "capability": "risk_severity", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "12372c8de13add55", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nUsing OGS risk severity levels (low/medium/high), classify the risk severity of the described pairing. Respond with just the severity level.\n\nINPUT:\n{\n \"dish\": \"simple grilled branzino with lemon\",\n \"beverage\": \"heavily oaked California Chardonnay\",\n \"risk_code\": \"RISK_OAK_MASKS\"\n}\n\nANSWER FORMAT: one_of:low,medium,high", "expected": { "value": "medium" }, "samples": [ { "sample": 0, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 597, "output_tokens": 1, "latency_ms": 1214.9, "usd": 0.001202, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 597, "output_tokens": 1, "latency_ms": 778.8, "usd": 0.001202, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 597, "output_tokens": 1, "latency_ms": 680.2, "usd": 0.001202, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 597.0, "output_tokens_mean": 1.0, "latency_ms_mean": 891.3, "usd_sum": 0.003606 } }, { "task_id": "ogs:core:benchmark-task:risk-018", "category": "risk", "capability": "risk_severity", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "7a97c002792dfad9", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nUsing OGS risk severity levels, classify the severity of a tannic red wine with raw anchovies.\n\nINPUT:\n{\n \"dish\": \"raw marinated anchovies\",\n \"beverage\": \"young tannic Cabernet Sauvignon\",\n \"risk_code\": \"RISK_TANNIN_FISH\"\n}\n\nANSWER FORMAT: one_of:low,medium,high", "expected": { "value": "high" }, "samples": [ { "sample": 0, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 587, "output_tokens": 1, "latency_ms": 565.1, "usd": 0.001182, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 587, "output_tokens": 1, "latency_ms": 615.2, "usd": 0.001182, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 587, "output_tokens": 1, "latency_ms": 605.6, "usd": 0.001182, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 587.0, "output_tokens_mean": 1.0, "latency_ms_mean": 595.3, "usd_sum": 0.003546 } }, { "task_id": "ogs:core:benchmark-task:risk-019", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "german", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "0e3d6c3f9d86af0b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"raw Kumamoto oyster\",\n \"beverage\": \"off-dry Spätlese Riesling with 45 g/L residual sugar\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SWEETNESS_CONFLICT" }, "samples": [ { "sample": 0, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 8, "latency_ms": 616.0, "usd": 0.001342, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 8, "latency_ms": 891.0, "usd": 0.001342, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 8, "latency_ms": 593.8, "usd": 0.001342, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 639.0, "output_tokens_mean": 8.0, "latency_ms_mean": 700.267, "usd_sum": 0.004026 } }, { "task_id": "ogs:core:benchmark-task:risk-020", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "2dd649d25c606ee7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"slow-braised oxtail stew with dark jus\",\n \"beverage\": \"very pale Provençal rosé, 12.5% abv\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_INTENSITY_MISMATCH" }, "samples": [ { "sample": 0, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_intensity_mismatch", "aliases": [] }, "metrics": { "input_tokens": 643, "output_tokens": 8, "latency_ms": 653.9, "usd": 0.00135, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_intensity_mismatch", "aliases": [] }, "metrics": { "input_tokens": 643, "output_tokens": 8, "latency_ms": 594.6, "usd": 0.00135, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_intensity_mismatch", "aliases": [] }, "metrics": { "input_tokens": 643, "output_tokens": 8, "latency_ms": 720.5, "usd": 0.00135, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 643.0, "output_tokens_mean": 8.0, "latency_ms_mean": 656.333, "usd_sum": 0.00405 } }, { "task_id": "ogs:core:benchmark-task:safe-001", "category": "safety", "capability": "cooking_temperature", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "8e37b185cfaed2aa", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nWhat is the minimum core temperature (°C) required to safely cook poultry under the OGS HACCP reference? Respond with a single number.\n\nINPUT:\n{\n \"product\": \"whole chicken\"\n}\n\nANSWER FORMAT: numeric:integer or decimal °C", "expected": { "value": 75, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 795, "output_tokens": 1, "latency_ms": 600.8, "usd": 0.001598, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 795, "output_tokens": 1, "latency_ms": 699.9, "usd": 0.001598, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 795, "output_tokens": 1, "latency_ms": 453.4, "usd": 0.001598, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 795.0, "output_tokens_mean": 1.0, "latency_ms_mean": 584.7, "usd_sum": 0.004794 } }, { "task_id": "ogs:core:benchmark-task:safe-002", "category": "safety", "capability": "cooking_temperature", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "d38d6470a18f7e97", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nA restaurant serves minced-beef smash burgers. What minimum core temperature (°C) should the patties reach? Respond with a single number.\n\nINPUT:\n{\n \"product\": \"minced beef patty\"\n}\n\nANSWER FORMAT: numeric:integer °C", "expected": { "value": 75, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 796, "output_tokens": 1, "latency_ms": 594.2, "usd": 0.0016, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 796, "output_tokens": 1, "latency_ms": 626.1, "usd": 0.0016, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 796, "output_tokens": 1, "latency_ms": 506.3, "usd": 0.0016, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 796.0, "output_tokens_mean": 1.0, "latency_ms_mean": 575.533, "usd_sum": 0.0048 } }, { "task_id": "ogs:core:benchmark-task:safe-003", "category": "safety", "capability": "danger_zone", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "97f1d8e6fc44b9e2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nThe bacterial danger zone is defined between two temperatures in °C. Respond as 'LOW-HIGH' in °C (integers), e.g. '10-50'.\n\nANSWER FORMAT: exact:LOW-HIGH °C", "expected": { "value": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "samples": [ { "sample": 0, "raw_response": "exact:5-63 °C", "compliant": true, "score": 0.0, "detail": { "predicted": "exact:5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 789, "output_tokens": 7, "latency_ms": 604.8, "usd": 0.001634, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "exact:5-63 °C", "compliant": true, "score": 0.0, "detail": { "predicted": "exact:5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 789, "output_tokens": 7, "latency_ms": 587.1, "usd": 0.001634, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "exact:5-63 °C", "compliant": true, "score": 0.0, "detail": { "predicted": "exact:5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 789, "output_tokens": 7, "latency_ms": 637.8, "usd": 0.001634, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 789.0, "output_tokens_mean": 7.0, "latency_ms_mean": 609.9, "usd_sum": 0.004902 } }, { "task_id": "ogs:core:benchmark-task:safe-004", "category": "safety", "capability": "cooling_rule", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "9e5770b6c7036769", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nUnder UK FSA guidance, hot food must be cooled from 63 °C down to 21 °C within how many hours? Respond with a single integer.\n\nANSWER FORMAT: numeric:integer hours", "expected": { "value": 2, "tolerance": 0 }, "samples": [ { "sample": 0, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 784, "output_tokens": 1, "latency_ms": 623.6, "usd": 0.001576, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 784, "output_tokens": 1, "latency_ms": 625.6, "usd": 0.001576, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 784, "output_tokens": 1, "latency_ms": 585.0, "usd": 0.001576, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 784.0, "output_tokens_mean": 1.0, "latency_ms_mean": 611.4, "usd_sum": 0.004728 } }, { "task_id": "ogs:core:benchmark-task:safe-005", "category": "safety", "capability": "reheating", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "cb2ff73059921b59", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nTo what minimum core temperature (°C) must a previously cooked and chilled dish be reheated under OGS HACCP? Respond with a single number.\n\nANSWER FORMAT: numeric:integer °C", "expected": { "value": 75, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 783, "output_tokens": 1, "latency_ms": 586.0, "usd": 0.001574, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 783, "output_tokens": 1, "latency_ms": 594.7, "usd": 0.001574, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "75°C", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 783, "output_tokens": 2, "latency_ms": 579.3, "usd": 0.001582, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 783.0, "output_tokens_mean": 1.333, "latency_ms_mean": 586.667, "usd_sum": 0.00473 } }, { "task_id": "ogs:core:benchmark-task:safe-006", "category": "safety", "capability": "hot_holding", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "b3c9f3a848d65390", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nWhat minimum temperature (°C) must hot food be held at for service? Respond with a single number.\n\nANSWER FORMAT: numeric:integer °C", "expected": { "value": 63, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "63", "compliant": true, "score": 1.0, "detail": { "predicted": 63.0, "expected": 63.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 774, "output_tokens": 1, "latency_ms": 610.9, "usd": 0.001556, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "63", "compliant": true, "score": 1.0, "detail": { "predicted": 63.0, "expected": 63.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 774, "output_tokens": 1, "latency_ms": 679.8, "usd": 0.001556, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "63", "compliant": true, "score": 1.0, "detail": { "predicted": 63.0, "expected": 63.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 774, "output_tokens": 1, "latency_ms": 602.2, "usd": 0.001556, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 774.0, "output_tokens_mean": 1.0, "latency_ms_mean": 630.967, "usd_sum": 0.004668 } }, { "task_id": "ogs:core:benchmark-task:safe-007", "category": "safety", "capability": "cold_chain", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "f120f4a38737e981", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nWhat is the maximum temperature (°C) for frozen storage under OGS HACCP? Respond with a single number (negative).\n\nANSWER FORMAT: numeric:integer °C", "expected": { "value": -18, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "-18", "compliant": true, "score": 1.0, "detail": { "predicted": -18.0, "expected": -18.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 778, "output_tokens": 2, "latency_ms": 610.9, "usd": 0.001572, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "-18", "compliant": true, "score": 1.0, "detail": { "predicted": -18.0, "expected": -18.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 778, "output_tokens": 2, "latency_ms": 662.5, "usd": 0.001572, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "-18", "compliant": true, "score": 1.0, "detail": { "predicted": -18.0, "expected": -18.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 778, "output_tokens": 2, "latency_ms": 585.9, "usd": 0.001572, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 778.0, "output_tokens_mean": 2.0, "latency_ms_mean": 619.767, "usd_sum": 0.004716 } }, { "task_id": "ogs:core:benchmark-task:safe-008", "category": "safety", "capability": "thawing_method", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "9b8f975bd042c7a0", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nWhich of the following thawing methods is explicitly NOT permitted under OGS HACCP: 'in the fridge at 4 °C', 'under cold running water', 'in the microwave just before cooking', 'at room temperature on the counter'? Respond with the exact method phrase.\n\nINPUT:\n{\n \"methods\": [\n \"in the fridge at 4 °C\",\n \"under cold running water\",\n \"in the microwave just before cooking\",\n \"at room temperature on the counter\"\n ]\n}\n\nANSWER FORMAT: exact:method phrase", "expected": { "value": "at room temperature on the counter", "aliases": [ "room temperature", "on the counter", "room-temperature thawing" ] }, "samples": [ { "sample": 0, "raw_response": "at room temperature on the counter", "compliant": true, "score": 1.0, "detail": { "predicted": "at room temperature on the counter", "expected": "at room temperature on the counter", "aliases": [ "room temperature", "on the counter", "room-temperature thawing" ] }, "metrics": { "input_tokens": 854, "output_tokens": 6, "latency_ms": 867.5, "usd": 0.001756, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "at room temperature on the counter", "compliant": true, "score": 1.0, "detail": { "predicted": "at room temperature on the counter", "expected": "at room temperature on the counter", "aliases": [ "room temperature", "on the counter", "room-temperature thawing" ] }, "metrics": { "input_tokens": 854, "output_tokens": 6, "latency_ms": 823.2, "usd": 0.001756, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "at room temperature on the counter", "compliant": true, "score": 1.0, "detail": { "predicted": "at room temperature on the counter", "expected": "at room temperature on the counter", "aliases": [ "room temperature", "on the counter", "room-temperature thawing" ] }, "metrics": { "input_tokens": 854, "output_tokens": 6, "latency_ms": 634.5, "usd": 0.001756, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 854.0, "output_tokens_mean": 6.0, "latency_ms_mean": 775.067, "usd_sum": 0.005268 } }, { "task_id": "ogs:core:benchmark-task:safe-009", "category": "safety", "capability": "ccp_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "set_f1", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "9f4b49c1c20e4376", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nFor a cook-chill dish of chicken curry with rice, identify the Critical Control Points from the OGS stage list. Return a comma-separated list using the OGS CCP stage IDs.\n\nINPUT:\n{\n \"dish\": \"cook-chill chicken curry with rice\"\n}\n\nANSWER FORMAT: set:comma-separated CCP stage IDs", "expected": { "values": [ "cooking", "cooling", "storage_cold", "reheating", "hot_holding" ] }, "samples": [ { "sample": 0, "raw_response": "receiving,storage_cold,prep,cooking,cooling,storage_cold,reheating,service", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "cooking", "cooling", "prep", "receiving", "reheating", "service", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.5714, "recall": 0.8 }, "metrics": { "input_tokens": 808, "output_tokens": 21, "latency_ms": 723.7, "usd": 0.001784, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "receiving,storage_cold,prep,cooking,cooling,storage_cold,reheating,service", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "cooking", "cooling", "prep", "receiving", "reheating", "service", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.5714, "recall": 0.8 }, "metrics": { "input_tokens": 808, "output_tokens": 21, "latency_ms": 767.3, "usd": 0.001784, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "receiving,storage_cold,prep,cooking,cooling,storage_cold,reheating,service", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "cooking", "cooling", "prep", "receiving", "reheating", "service", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.5714, "recall": 0.8 }, "metrics": { "input_tokens": 808, "output_tokens": 21, "latency_ms": 1109.1, "usd": 0.001784, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.6667, "ci95_hi": 0.6667, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 808.0, "output_tokens_mean": 21.0, "latency_ms_mean": 866.7, "usd_sum": 0.005352 } }, { "task_id": "ogs:core:benchmark-task:safe-010", "category": "safety", "capability": "cooking_temperature", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "eea6814938f18565", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nA bistro serves a rare whole-muscle ribeye (seared exterior, internal 46 °C). Under OGS HACCP, is this permitted? Answer yes or no.\n\nINPUT:\n{\n \"product\": \"whole-muscle ribeye\",\n \"core_c\": 46\n}\n\nANSWER FORMAT: exact:yes|no", "expected": { "value": "yes" }, "samples": [ { "sample": 0, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 812, "output_tokens": 1, "latency_ms": 649.9, "usd": 0.001632, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 812, "output_tokens": 1, "latency_ms": 606.9, "usd": 0.001632, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 812, "output_tokens": 1, "latency_ms": 574.4, "usd": 0.001632, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 812.0, "output_tokens_mean": 1.0, "latency_ms_mean": 610.4, "usd_sum": 0.004896 } }, { "task_id": "ogs:core:benchmark-task:safe-011", "category": "safety", "capability": "at_risk_groups", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "edc2981cec11c39e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nA children's hospital must serve hollandaise sauce. Which is the ONE compliant option: 'fresh shell eggs at 63 °C', 'fresh shell eggs at 70 °C', 'pasteurised egg yolk', 'raw shell eggs with lemon juice'? Respond with the exact phrase.\n\nINPUT:\n{\n \"options\": [\n \"fresh shell eggs at 63 °C\",\n \"fresh shell eggs at 70 °C\",\n \"pasteurised egg yolk\",\n \"raw shell eggs with lemon juice\"\n ]\n}\n\nANSWER FORMAT: exact:option phrase", "expected": { "value": "pasteurised egg yolk", "aliases": [ "pasteurised egg", "pasteurized egg yolk", "pasteurized egg" ] }, "samples": [ { "sample": 0, "raw_response": "pasteurised egg yolk", "compliant": true, "score": 1.0, "detail": { "predicted": "pasteurised egg yolk", "expected": "pasteurised egg yolk", "aliases": [ "pasteurised egg", "pasteurized egg yolk", "pasteurized egg" ] }, "metrics": { "input_tokens": 861, "output_tokens": 6, "latency_ms": 647.9, "usd": 0.00177, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "pasteurised egg yolk", "compliant": true, "score": 1.0, "detail": { "predicted": "pasteurised egg yolk", "expected": "pasteurised egg yolk", "aliases": [ "pasteurised egg", "pasteurized egg yolk", "pasteurized egg" ] }, "metrics": { "input_tokens": 861, "output_tokens": 6, "latency_ms": 1076.1, "usd": 0.00177, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "pasteurised egg yolk", "compliant": true, "score": 1.0, "detail": { "predicted": "pasteurised egg yolk", "expected": "pasteurised egg yolk", "aliases": [ "pasteurised egg", "pasteurized egg yolk", "pasteurized egg" ] }, "metrics": { "input_tokens": 861, "output_tokens": 6, "latency_ms": 611.0, "usd": 0.00177, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 861.0, "output_tokens_mean": 6.0, "latency_ms_mean": 778.333, "usd_sum": 0.00531 } }, { "task_id": "ogs:core:benchmark-task:safe-012", "category": "safety", "capability": "numeric_vector", "difficulty": "hard", "cuisine_region": "global", "scorer": "numeric_vector_mae", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "2ba4113ffe26b2fc", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nReturn the canonical HACCP reference temperatures in °C for this dish flow (poultry cook-chill operation): [cold_storage_max, poultry_core_cook_min, hot_hold_min, reheat_min, frozen_storage_max]. Respond with a JSON array of five numbers only, in that order.\n\nINPUT:\n{\n \"flow\": \"poultry cook-chill\"\n}\n\nANSWER FORMAT: json:array of 5 numbers", "expected": { "values": [ 5, 75, 63, 75, -18 ] }, "samples": [ { "sample": 0, "raw_response": "[5,75,63,75,-18]", "compliant": true, "score": 1.0, "detail": { "per_position": [ { "index": 0, "predicted": 5, "expected": 5, "score": 1.0 }, { "index": 1, "predicted": 75, "expected": 75, "score": 1.0 }, { "index": 2, "predicted": 63, "expected": 63, "score": 1.0 }, { "index": 3, "predicted": 75, "expected": 75, "score": 1.0 }, { "index": 4, "predicted": -18, "expected": -18, "score": 1.0 } ], "tolerance": 1.0 }, "metrics": { "input_tokens": 830, "output_tokens": 11, "latency_ms": 824.1, "usd": 0.001748, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[5,75,63,75,-18]", "compliant": true, "score": 1.0, "detail": { "per_position": [ { "index": 0, "predicted": 5, "expected": 5, "score": 1.0 }, { "index": 1, "predicted": 75, "expected": 75, "score": 1.0 }, { "index": 2, "predicted": 63, "expected": 63, "score": 1.0 }, { "index": 3, "predicted": 75, "expected": 75, "score": 1.0 }, { "index": 4, "predicted": -18, "expected": -18, "score": 1.0 } ], "tolerance": 1.0 }, "metrics": { "input_tokens": 830, "output_tokens": 11, "latency_ms": 574.6, "usd": 0.001748, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[5,75,63,75,-18]", "compliant": true, "score": 1.0, "detail": { "per_position": [ { "index": 0, "predicted": 5, "expected": 5, "score": 1.0 }, { "index": 1, "predicted": 75, "expected": 75, "score": 1.0 }, { "index": 2, "predicted": 63, "expected": 63, "score": 1.0 }, { "index": 3, "predicted": 75, "expected": 75, "score": 1.0 }, { "index": 4, "predicted": -18, "expected": -18, "score": 1.0 } ], "tolerance": 1.0 }, "metrics": { "input_tokens": 830, "output_tokens": 11, "latency_ms": 688.6, "usd": 0.001748, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 830.0, "output_tokens_mean": 11.0, "latency_ms_mean": 695.767, "usd_sum": 0.005244 } }, { "task_id": "ogs:core:benchmark-task:sense-001", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "italian", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "913118356da8150b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the umami intensity of a 36-month aged Parmigiano-Reggiano on the OGS 0-10 intensity scale (0 = not present, 10 = extreme). Respond with only a single decimal number.\n\nINPUT:\n{\n \"ingredient\": \"Parmigiano-Reggiano 36 months\",\n \"attribute\": \"umami\"\n}\n\nANSWER FORMAT: integer_0_10", "expected": { "value": 8.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "8.5", "compliant": true, "score": 1.0, "detail": { "predicted": 8.5, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 379, "output_tokens": 3, "latency_ms": 631.6, "usd": 0.000782, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 1.0, "detail": { "predicted": 8.5, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 379, "output_tokens": 3, "latency_ms": 668.8, "usd": 0.000782, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.0, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 379, "output_tokens": 3, "latency_ms": 646.8, "usd": 0.000782, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.8889, "score_summary": { "mean": 0.8889, "stdev": 0.1924, "sem": 0.1111, "ci95_lo": 0.6711, "ci95_hi": 1.1067, "n": 3 }, "score_if_valid": 0.8889, "format_rate": 1.0, "metrics": { "input_tokens_mean": 379.0, "output_tokens_mean": 3.0, "latency_ms_mean": 649.067, "usd_sum": 0.002346 } }, { "task_id": "ogs:core:benchmark-task:sense-002", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "2690028d89b60292", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the sour intensity of undiluted fresh lemon juice on the OGS 0-10 intensity scale. Respond with only a single decimal number.\n\nINPUT:\n{\n \"ingredient\": \"fresh lemon juice (undiluted)\",\n \"attribute\": \"sour\"\n}\n\nANSWER FORMAT: integer_0_10", "expected": { "value": 9.5, "tolerance": 1.0 }, "samples": [ { "sample": 0, "raw_response": "9.0", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 361, "output_tokens": 3, "latency_ms": 589.6, "usd": 0.000746, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "9.0", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 361, "output_tokens": 3, "latency_ms": 579.6, "usd": 0.000746, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "9.0", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 361, "output_tokens": 3, "latency_ms": 525.3, "usd": 0.000746, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.5, "score_summary": { "mean": 0.5, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.5, "ci95_hi": 0.5, "n": 3 }, "score_if_valid": 0.5, "format_rate": 1.0, "metrics": { "input_tokens_mean": 361.0, "output_tokens_mean": 3.0, "latency_ms_mean": 564.833, "usd_sum": 0.002238 } }, { "task_id": "ogs:core:benchmark-task:sense-003", "category": "sensory", "capability": "structural_estimation", "difficulty": "medium", "cuisine_region": "italian", "scorer": "numeric_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "b09502eb4fd5d61f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nEstimate the tannin intensity of a young (under 5 years old) Barolo on the OGS 0-10 intensity scale. Respond with only a single decimal number.\n\nINPUT:\n{\n \"beverage\": \"young Barolo, <5 years\",\n \"attribute\": \"tannin\"\n}\n\nANSWER FORMAT: integer_0_10", "expected": { "value": 8.5, "tolerance": 1.0 }, "samples": [ { "sample": 0, "raw_response": "8", "compliant": true, "score": 0.5, "detail": { "predicted": 8.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 589.1, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8", "compliant": true, "score": 0.5, "detail": { "predicted": 8.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 572.6, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8", "compliant": true, "score": 0.5, "detail": { "predicted": 8.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 349, "output_tokens": 1, "latency_ms": 990.5, "usd": 0.000706, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.5, "score_summary": { "mean": 0.5, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.5, "ci95_hi": 0.5, "n": 3 }, "score_if_valid": 0.5, "format_rate": 1.0, "metrics": { "input_tokens_mean": 349.0, "output_tokens_mean": 1.0, "latency_ms_mean": 717.4, "usd_sum": 0.002118 } }, { "task_id": "ogs:core:benchmark-task:sense-004", "category": "sensory", "capability": "basic_taste_vector", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "94f009713056d52f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nReturn the five basic tastes for a ripe, in-season strawberry, each on the OGS 0-10 intensity scale. Respond as a single JSON object with keys sweet, sour, salty, bitter, umami.\n\nINPUT:\n{\n \"ingredient\": \"ripe, in-season strawberry\"\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"object\",\n \"required\": [\n \"sweet\",\n \"sour\",\n \"salty\",\n \"bitter\",\n \"umami\"\n ],\n \"properties\": {\n \"sweet\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"sour\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"salty\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"bitter\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"umami\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": false\n}", "expected": { "values": { "sweet": 7.0, "sour": 4.0, "salty": 0.5, "bitter": 1.0, "umami": 0.5 } }, "samples": [ { "sample": 0, "raw_response": "{\n \"sweet\": 7.5,\n \"sour\": 4,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n}", "compliant": true, "score": 0.8, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 4, "expected": 4.0, "score": 1.0 }, "salty": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.5, "expected": 1.0, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.5, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 567, "output_tokens": 45, "latency_ms": 971.9, "usd": 0.001494, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"sweet\": 7.5,\n \"sour\": 3.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n}", "compliant": true, "score": 0.75, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 3.5, "expected": 4.0, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.5, "expected": 1.0, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.5, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 567, "output_tokens": 47, "latency_ms": 806.8, "usd": 0.00151, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"sweet\": 7.5,\n \"sour\": 3.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n}", "compliant": true, "score": 0.75, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 3.5, "expected": 4.0, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.5, "expected": 1.0, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.5, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 567, "output_tokens": 47, "latency_ms": 809.8, "usd": 0.00151, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7667, "score_summary": { "mean": 0.7667, "stdev": 0.0289, "sem": 0.0167, "ci95_lo": 0.734, "ci95_hi": 0.7993, "n": 3 }, "score_if_valid": 0.7667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 567.0, "output_tokens_mean": 46.333, "latency_ms_mean": 862.833, "usd_sum": 0.004514 } }, { "task_id": "ogs:core:benchmark-task:sense-005", "category": "sensory", "capability": "structural_estimation", "difficulty": "medium", "cuisine_region": "american", "scorer": "numeric_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "c950ec9851ad52bf", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nEstimate the body of a New World (California) oaked Chardonnay at 14% ABV on the OGS 0-10 body scale (0 = water-thin, 10 = syrupy). Respond with only a single decimal number.\n\nINPUT:\n{\n \"beverage\": \"oaked California Chardonnay, 14% ABV\",\n \"attribute\": \"body\"\n}\n\nANSWER FORMAT: integer_0_10", "expected": { "value": 7.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "7", "compliant": true, "score": 1.0, "detail": { "predicted": 7.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 365, "output_tokens": 1, "latency_ms": 606.8, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "7", "compliant": true, "score": 1.0, "detail": { "predicted": 7.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 365, "output_tokens": 1, "latency_ms": 548.4, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "7", "compliant": true, "score": 1.0, "detail": { "predicted": 7.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 365, "output_tokens": 1, "latency_ms": 944.4, "usd": 0.000738, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 365.0, "output_tokens_mean": 1.0, "latency_ms_mean": 699.867, "usd_sum": 0.002214 } }, { "task_id": "ogs:core:benchmark-task:sense-006", "category": "sensory", "capability": "dominant_aromatic_family", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "d68ef8562addd55d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nIdentify the single dominant aromatic FAMILY (from the OGS vocabulary) of a classic Marlborough Sauvignon Blanc. Respond with just the family name.\n\nINPUT:\n{\n \"beverage\": \"Marlborough Sauvignon Blanc\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "vegetal" }, "samples": [ { "sample": 0, "raw_response": "fruit", "compliant": true, "score": 0.0, "detail": { "predicted": "fruit", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 330, "output_tokens": 1, "latency_ms": 609.1, "usd": 0.000668, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 0.0, "detail": { "predicted": "fruit", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 330, "output_tokens": 1, "latency_ms": 561.9, "usd": 0.000668, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 0.0, "detail": { "predicted": "fruit", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 330, "output_tokens": 1, "latency_ms": 618.0, "usd": 0.000668, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 330.0, "output_tokens_mean": 1.0, "latency_ms_mean": 596.333, "usd_sum": 0.002004 } }, { "task_id": "ogs:core:benchmark-task:sense-007", "category": "sensory", "capability": "structural_vector", "difficulty": "hard", "cuisine_region": "french", "scorer": "numeric_vector_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "658c14cce434cc0a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nReturn the OGS structural attributes of a Brut Champagne on the 0-10 scale. Respond as a JSON object with keys body, acidity_perception, tannin, astringency, alcohol_heat, effervescence.\n\nINPUT:\n{\n \"beverage\": \"Brut non-vintage Champagne\"\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"object\",\n \"required\": [\n \"body\",\n \"acidity_perception\",\n \"tannin\",\n \"astringency\",\n \"alcohol_heat\",\n \"effervescence\"\n ],\n \"properties\": {\n \"body\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"acidity_perception\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"tannin\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"astringency\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"alcohol_heat\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"effervescence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": false\n}", "expected": { "values": { "body": 4.5, "acidity_perception": 8.0, "tannin": 0.5, "astringency": 1.0, "alcohol_heat": 3.5, "effervescence": 9.0 } }, "samples": [ { "sample": 0, "raw_response": "{\n \"body\": 4,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 2,\n \"effervescence\": 8\n}", "compliant": true, "score": 0.7083, "detail": { "per_key": { "body": { "predicted": 4, "expected": 4.5, "score": 0.75 }, "acidity_perception": { "predicted": 8, "expected": 8.0, "score": 1.0 }, "tannin": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "astringency": { "predicted": 1, "expected": 1.0, "score": 1.0 }, "alcohol_heat": { "predicted": 2, "expected": 3.5, "score": 0.25 }, "effervescence": { "predicted": 8, "expected": 9.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 594, "output_tokens": 54, "latency_ms": 976.5, "usd": 0.00162, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"body\": 4,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 2,\n \"alcohol_heat\": 3,\n \"effervescence\": 8\n}", "compliant": true, "score": 0.7083, "detail": { "per_key": { "body": { "predicted": 4, "expected": 4.5, "score": 0.75 }, "acidity_perception": { "predicted": 8, "expected": 8.0, "score": 1.0 }, "tannin": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "astringency": { "predicted": 2, "expected": 1.0, "score": 0.5 }, "alcohol_heat": { "predicted": 3, "expected": 3.5, "score": 0.75 }, "effervescence": { "predicted": 8, "expected": 9.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 594, "output_tokens": 54, "latency_ms": 810.7, "usd": 0.00162, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"body\": 4,\n \"acidity_perception\": 7,\n \"tannin\": 0,\n \"astringency\": 2,\n \"alcohol_heat\": 3,\n \"effervescence\": 8\n}", "compliant": true, "score": 0.625, "detail": { "per_key": { "body": { "predicted": 4, "expected": 4.5, "score": 0.75 }, "acidity_perception": { "predicted": 7, "expected": 8.0, "score": 0.5 }, "tannin": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "astringency": { "predicted": 2, "expected": 1.0, "score": 0.5 }, "alcohol_heat": { "predicted": 3, "expected": 3.5, "score": 0.75 }, "effervescence": { "predicted": 8, "expected": 9.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 594, "output_tokens": 54, "latency_ms": 826.3, "usd": 0.00162, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6805, "score_summary": { "mean": 0.6805, "stdev": 0.0481, "sem": 0.0278, "ci95_lo": 0.6261, "ci95_hi": 0.735, "n": 3 }, "score_if_valid": 0.6805, "format_rate": 1.0, "metrics": { "input_tokens_mean": 594.0, "output_tokens_mean": 54.0, "latency_ms_mean": 871.167, "usd_sum": 0.00486 } }, { "task_id": "ogs:core:benchmark-task:sense-008", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "italian", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "873c6c2f9608e43f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the bitter intensity of raw radicchio on the OGS 0-10 intensity scale. Respond with only a single decimal number.\n\nINPUT:\n{\n \"ingredient\": \"raw radicchio\",\n \"attribute\": \"bitter\"\n}\n\nANSWER FORMAT: integer_0_10", "expected": { "value": 6.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "7.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 356, "output_tokens": 3, "latency_ms": 559.4, "usd": 0.000736, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "6.5", "compliant": true, "score": 1.0, "detail": { "predicted": 6.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 356, "output_tokens": 3, "latency_ms": 645.9, "usd": 0.000736, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "7.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 356, "output_tokens": 3, "latency_ms": 625.9, "usd": 0.000736, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7778, "score_summary": { "mean": 0.7778, "stdev": 0.1924, "sem": 0.1111, "ci95_lo": 0.56, "ci95_hi": 0.9956, "n": 3 }, "score_if_valid": 0.7778, "format_rate": 1.0, "metrics": { "input_tokens_mean": 356.0, "output_tokens_mean": 3.0, "latency_ms_mean": 610.4, "usd_sum": 0.002208 } }, { "task_id": "ogs:core:benchmark-task:sense-009", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "523e04f39252cb4b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the umami intensity of a plain 10-minute cold-steep kombu dashi on the OGS 0-10 scale. Respond with only a single decimal number.\n\nINPUT:\n{\n \"ingredient\": \"kombu dashi (cold steep 10 min, 10 g/L Hokkaido kombu)\",\n \"attribute\": \"umami\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 6.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "2.6", "compliant": true, "score": 0.0, "detail": { "predicted": 2.6, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 380, "output_tokens": 3, "latency_ms": 553.4, "usd": 0.000784, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "3.5", "compliant": true, "score": 0.0, "detail": { "predicted": 3.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 380, "output_tokens": 3, "latency_ms": 589.3, "usd": 0.000784, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "2.5", "compliant": true, "score": 0.0, "detail": { "predicted": 2.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 380, "output_tokens": 3, "latency_ms": 631.9, "usd": 0.000784, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 380.0, "output_tokens_mean": 3.0, "latency_ms_mean": 591.533, "usd_sum": 0.002352 } }, { "task_id": "ogs:core:benchmark-task:sense-010", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "1813cae53ba17a84", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the bitter intensity of a square of unsweetened 85% cacao dark chocolate on the OGS 0-10 scale.\n\nINPUT:\n{\n \"ingredient\": \"single-origin 85% dark chocolate\",\n \"attribute\": \"bitter\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 6.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "7.5", "compliant": true, "score": 0.3333, "detail": { "predicted": 7.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 358, "output_tokens": 3, "latency_ms": 606.1, "usd": 0.00074, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "7.5", "compliant": true, "score": 0.3333, "detail": { "predicted": 7.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 358, "output_tokens": 3, "latency_ms": 623.6, "usd": 0.00074, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "7.5", "compliant": true, "score": 0.3333, "detail": { "predicted": 7.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 358, "output_tokens": 3, "latency_ms": 573.4, "usd": 0.00074, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.3333, "ci95_hi": 0.3333, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 358.0, "output_tokens_mean": 3.0, "latency_ms_mean": 601.033, "usd_sum": 0.00222 } }, { "task_id": "ogs:core:benchmark-task:sense-011", "category": "sensory", "capability": "structural_estimation", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "numeric_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "1886b2e009716d1d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nEstimate the perceived acidity of freshly squeezed yuzu juice on the OGS 0-10 scale.\n\nINPUT:\n{\n \"ingredient\": \"fresh yuzu juice\",\n \"attribute\": \"acidity_perception\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 9.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "8", "compliant": true, "score": 0.3333, "detail": { "predicted": 8.0, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 331, "output_tokens": 1, "latency_ms": 589.6, "usd": 0.00067, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "9", "compliant": true, "score": 1.0, "detail": { "predicted": 9.0, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 331, "output_tokens": 1, "latency_ms": 622.3, "usd": 0.00067, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8", "compliant": true, "score": 0.3333, "detail": { "predicted": 8.0, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 331, "output_tokens": 1, "latency_ms": 558.2, "usd": 0.00067, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.5555, "score_summary": { "mean": 0.5555, "stdev": 0.3849, "sem": 0.2222, "ci95_lo": 0.12, "ci95_hi": 0.9911, "n": 3 }, "score_if_valid": 0.5555, "format_rate": 1.0, "metrics": { "input_tokens_mean": 331.0, "output_tokens_mean": 1.0, "latency_ms_mean": 590.033, "usd_sum": 0.00201 } }, { "task_id": "ogs:core:benchmark-task:sense-012", "category": "sensory", "capability": "basic_taste_vector", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "8d40a83f1b501685", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nReturn the five basic tastes of fresh-squeezed Valencia orange juice on the OGS 0-10 scale as a JSON object with keys sweet, sour, salty, bitter, umami. Respond with ONLY the JSON.\n\nINPUT:\n{\n \"ingredient\": \"freshly squeezed Valencia orange juice\"\n}\n\nANSWER FORMAT: json", "expected": { "values": { "sweet": 7.0, "sour": 5.5, "salty": 0.0, "bitter": 0.5, "umami": 0.0 } }, "samples": [ { "sample": 0, "raw_response": "{\n \"sweet\": 6.5,\n \"sour\": 4.0,\n \"salty\": 0.0,\n \"bitter\": 0.5,\n \"umami\": 0.0\n}", "compliant": true, "score": 0.8, "detail": { "per_key": { "sweet": { "predicted": 6.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 4.0, "expected": 5.5, "score": 0.25 }, "salty": { "predicted": 0.0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 0.5, "expected": 0.5, "score": 1.0 }, "umami": { "predicted": 0.0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 364, "output_tokens": 51, "latency_ms": 825.1, "usd": 0.001136, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"sweet\": 6.5,\n \"sour\": 5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n}", "compliant": true, "score": 0.9, "detail": { "per_key": { "sweet": { "predicted": 6.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 5, "expected": 5.5, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 0.5, "expected": 0.5, "score": 1.0 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 364, "output_tokens": 45, "latency_ms": 802.8, "usd": 0.001088, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"sweet\": 6,\n \"sour\": 5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n}", "compliant": true, "score": 0.85, "detail": { "per_key": { "sweet": { "predicted": 6, "expected": 7.0, "score": 0.5 }, "sour": { "predicted": 5, "expected": 5.5, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 0.5, "expected": 0.5, "score": 1.0 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 364, "output_tokens": 43, "latency_ms": 774.3, "usd": 0.001072, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.85, "score_summary": { "mean": 0.85, "stdev": 0.05, "sem": 0.0289, "ci95_lo": 0.7934, "ci95_hi": 0.9066, "n": 3 }, "score_if_valid": 0.85, "format_rate": 1.0, "metrics": { "input_tokens_mean": 364.0, "output_tokens_mean": 46.333, "latency_ms_mean": 800.733, "usd_sum": 0.003296 } }, { "task_id": "ogs:core:benchmark-task:sense-013", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "middle_eastern", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "691f59088f3e98f3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the sweet intensity of a fresh Medjool date on the OGS 0-10 scale.\n\nINPUT:\n{\n \"ingredient\": \"Medjool date, soft and ripe\",\n \"attribute\": \"sweet\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 9.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 352, "output_tokens": 3, "latency_ms": 678.3, "usd": 0.000728, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 352, "output_tokens": 3, "latency_ms": 599.5, "usd": 0.000728, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "9", "compliant": true, "score": 1.0, "detail": { "predicted": 9.0, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 352, "output_tokens": 1, "latency_ms": 543.2, "usd": 0.000712, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7778, "score_summary": { "mean": 0.7778, "stdev": 0.1924, "sem": 0.1111, "ci95_lo": 0.56, "ci95_hi": 0.9956, "n": 3 }, "score_if_valid": 0.7778, "format_rate": 1.0, "metrics": { "input_tokens_mean": 352.0, "output_tokens_mean": 2.333, "latency_ms_mean": 607.0, "usd_sum": 0.002168 } }, { "task_id": "ogs:core:benchmark-task:sense-014", "category": "sensory", "capability": "dominant_aromatic_family", "difficulty": "medium", "cuisine_region": "scottish", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "c4a83a79265c0e9f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nIdentify the single dominant aromatic FAMILY (OGS vocabulary) of a heavily-peated Islay single malt (e.g. Ardbeg 10).\n\nINPUT:\n{\n \"item\": \"heavily peated Islay single malt whisky, ~50 ppm phenols\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "wood" }, "samples": [ { "sample": 0, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 342, "output_tokens": 1, "latency_ms": 610.4, "usd": 0.000692, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 342, "output_tokens": 1, "latency_ms": 810.0, "usd": 0.000692, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 342, "output_tokens": 1, "latency_ms": 581.1, "usd": 0.000692, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 342.0, "output_tokens_mean": 1.0, "latency_ms_mean": 667.167, "usd_sum": 0.002076 } }, { "task_id": "ogs:core:benchmark-task:sense-015", "category": "sensory", "capability": "structural_vector", "difficulty": "hard", "cuisine_region": "italian", "scorer": "numeric_vector_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "66d64ca2254c09ee", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nReturn the OGS structural attributes of a 5-year-old Amarone della Valpolicella on the 0-10 scale. Respond with a JSON object with keys body, acidity_perception, tannin, astringency, alcohol_heat, effervescence. JSON only.\n\nINPUT:\n{\n \"item\": \"Amarone della Valpolicella Classico, 5 years old, 16% abv\"\n}\n\nANSWER FORMAT: json", "expected": { "values": { "body": 9.0, "acidity_perception": 6.0, "tannin": 7.0, "astringency": 5.5, "alcohol_heat": 8.5, "effervescence": 0.0 } }, "samples": [ { "sample": 0, "raw_response": "{\n \"body\": 9,\n \"acidity_perception\": 5,\n \"tannin\": 7,\n \"astringency\": 6,\n \"alcohol_heat\": 9,\n \"effervescence\": 0\n}", "compliant": true, "score": 0.8333, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 5, "expected": 6.0, "score": 0.5 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 6, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 9, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 371, "output_tokens": 54, "latency_ms": 1232.3, "usd": 0.001174, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"body\": 9,\n \"acidity_perception\": 5,\n \"tannin\": 6,\n \"astringency\": 5,\n \"alcohol_heat\": 8,\n \"effervescence\": 0\n}", "compliant": true, "score": 0.75, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 5, "expected": 6.0, "score": 0.5 }, "tannin": { "predicted": 6, "expected": 7.0, "score": 0.5 }, "astringency": { "predicted": 5, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 371, "output_tokens": 54, "latency_ms": 785.1, "usd": 0.001174, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"body\": 9,\n \"acidity_perception\": 5,\n \"tannin\": 7,\n \"astringency\": 6,\n \"alcohol_heat\": 8,\n \"effervescence\": 0\n}", "compliant": true, "score": 0.8333, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 5, "expected": 6.0, "score": 0.5 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 6, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 371, "output_tokens": 54, "latency_ms": 933.6, "usd": 0.001174, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.8055, "score_summary": { "mean": 0.8055, "stdev": 0.0481, "sem": 0.0278, "ci95_lo": 0.7511, "ci95_hi": 0.86, "n": 3 }, "score_if_valid": 0.8055, "format_rate": 1.0, "metrics": { "input_tokens_mean": 371.0, "output_tokens_mean": 54.0, "latency_ms_mean": 983.667, "usd_sum": 0.003522 } }, { "task_id": "ogs:core:benchmark-task:sense-016", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "spanish", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "70318c6fd3b033d2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the umami intensity of 24-month acorn-finished jamón ibérico de bellota on the OGS 0-10 scale.\n\nINPUT:\n{\n \"ingredient\": \"jamón ibérico de bellota, 24 months, acorn-finished\",\n \"attribute\": \"umami\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 8.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "7.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 370, "output_tokens": 3, "latency_ms": 574.0, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "7.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 370, "output_tokens": 3, "latency_ms": 814.8, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "7.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 370, "output_tokens": 3, "latency_ms": 596.1, "usd": 0.000764, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.6667, "ci95_hi": 0.6667, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 370.0, "output_tokens_mean": 3.0, "latency_ms_mean": 661.633, "usd_sum": 0.002292 } }, { "task_id": "ogs:core:benchmark-task:sense-017", "category": "sensory", "capability": "dominant_aromatic_family", "difficulty": "medium", "cuisine_region": "thai", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "c3cedde89152ce76", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nIdentify the single dominant aromatic FAMILY of fresh Thai basil (horapa) leaves.\n\nINPUT:\n{\n \"item\": \"fresh Thai basil (horapa), whole leaves\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "herbal" }, "samples": [ { "sample": 0, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 321, "output_tokens": 2, "latency_ms": 1410.1, "usd": 0.000658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 321, "output_tokens": 2, "latency_ms": 1072.9, "usd": 0.000658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 321, "output_tokens": 2, "latency_ms": 614.7, "usd": 0.000658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 321.0, "output_tokens_mean": 2.0, "latency_ms_mean": 1032.567, "usd_sum": 0.001974 } }, { "task_id": "ogs:core:benchmark-task:sense-018", "category": "sensory", "capability": "structural_estimation", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "7d31de11173a7fd2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nEstimate the body of a dry Provençal rosé (e.g. Côtes de Provence Grenache-led) on the OGS 0-10 scale.\n\nINPUT:\n{\n \"item\": \"dry Provençal rosé, 12.5% abv, minimal skin contact\",\n \"attribute\": \"body\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 3.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 353, "output_tokens": 1, "latency_ms": 686.4, "usd": 0.000714, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 353, "output_tokens": 1, "latency_ms": 569.4, "usd": 0.000714, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 353, "output_tokens": 1, "latency_ms": 642.8, "usd": 0.000714, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.6667, "ci95_hi": 0.6667, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 353.0, "output_tokens_mean": 1.0, "latency_ms_mean": 632.867, "usd_sum": 0.002142 } }, { "task_id": "ogs:core:benchmark-task:sense-019", "category": "sensory", "capability": "basic_taste_vector", "difficulty": "hard", "cuisine_region": "korean", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "2e7df899a0148ebd", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nReturn the five basic tastes of well-fermented napa kimchi (6 weeks at 4°C after 2 days at room temp) as a JSON object.\n\nINPUT:\n{\n \"ingredient\": \"napa kimchi, 6 weeks fermented, ripe\"\n}\n\nANSWER FORMAT: json", "expected": { "values": { "sweet": 1.0, "sour": 7.0, "salty": 6.0, "bitter": 1.5, "umami": 7.0 } }, "samples": [ { "sample": 0, "raw_response": "{\n \"sweet\": 1.5,\n \"sour\": 7.5,\n \"salty\": 5.5,\n \"bitter\": 2.5,\n \"umami\": 6\n}", "compliant": true, "score": 0.65, "detail": { "per_key": { "sweet": { "predicted": 1.5, "expected": 1.0, "score": 0.75 }, "sour": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "salty": { "predicted": 5.5, "expected": 6.0, "score": 0.75 }, "bitter": { "predicted": 2.5, "expected": 1.5, "score": 0.5 }, "umami": { "predicted": 6, "expected": 7.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 355, "output_tokens": 49, "latency_ms": 792.3, "usd": 0.001102, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"sweet\": 2.5,\n \"sour\": 7.5,\n \"salty\": 6,\n \"bitter\": 1.5,\n \"umami\": 6.5\n}", "compliant": true, "score": 0.75, "detail": { "per_key": { "sweet": { "predicted": 2.5, "expected": 1.0, "score": 0.25 }, "sour": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "salty": { "predicted": 6, "expected": 6.0, "score": 1.0 }, "bitter": { "predicted": 1.5, "expected": 1.5, "score": 1.0 }, "umami": { "predicted": 6.5, "expected": 7.0, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 355, "output_tokens": 49, "latency_ms": 835.4, "usd": 0.001102, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"sweet\": 2.5,\n \"sour\": 7.5,\n \"salty\": 5.5,\n \"bitter\": 2,\n \"umami\": 8\n}", "compliant": true, "score": 0.6, "detail": { "per_key": { "sweet": { "predicted": 2.5, "expected": 1.0, "score": 0.25 }, "sour": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "salty": { "predicted": 5.5, "expected": 6.0, "score": 0.75 }, "bitter": { "predicted": 2, "expected": 1.5, "score": 0.75 }, "umami": { "predicted": 8, "expected": 7.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 355, "output_tokens": 47, "latency_ms": 820.7, "usd": 0.001086, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0764, "sem": 0.0441, "ci95_lo": 0.5802, "ci95_hi": 0.7531, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 355.0, "output_tokens_mean": 48.333, "latency_ms_mean": 816.133, "usd_sum": 0.00329 } }, { "task_id": "ogs:core:benchmark-task:sense-020", "category": "sensory", "capability": "structural_estimation", "difficulty": "medium", "cuisine_region": "portuguese", "scorer": "numeric_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "ca5b9ab85fe71acb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nEstimate the effervescence of a typical young Vinho Verde (traditional style with slight spritz) on the OGS 0-10 scale.\n\nINPUT:\n{\n \"item\": \"young Vinho Verde, slightly spritzig\",\n \"attribute\": \"effervescence\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 2.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 345, "output_tokens": 1, "latency_ms": 588.0, "usd": 0.000698, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 345, "output_tokens": 1, "latency_ms": 742.2, "usd": 0.000698, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 345, "output_tokens": 1, "latency_ms": 648.4, "usd": 0.000698, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.6667, "ci95_hi": 0.6667, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 345.0, "output_tokens_mean": 1.0, "latency_ms_mean": 659.533, "usd_sum": 0.002094 } }, { "task_id": "ogs:core:benchmark-task:struct-001", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "medium", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "4523d68b7da194f7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'fleur de sel' as an OGS ingredient. It MUST validate against the OGS ingredient schema (schema/ingredient.schema.json). Respond with ONLY the JSON object, no markdown fences.\n\nINPUT:\n{\n \"ingredient_name\": \"Fleur de sel\",\n \"namespace\": \"core\",\n \"id_slug\": \"fleur-de-sel\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:fleur-de-sel", "ogs_version": "0.1.0", "category": "salt" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:fleur-de-sel\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Fleur de sel\",\n \"fr\": \"Fleur de sel\"\n },\n \"category\": \"salt\",\n \"description\": {\n \"en\": \"Fleur de sel is a delicate, flaky sea salt hand-harvested from the surface of salt ponds, prized for its clean, bright flavor and subtle mineral notes.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 8.5,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 1,\n \"acidity_perception\": 0,\n \"tannin\": 0,\n \"astringency\": 0.2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"briny\",\n \"intensity\": 2\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea\",\n \"item\": \"ocean breeze\",\n \"intensity\": 1.5\n }\n ],\n \"texture\": [\n \"crunchy\",\n \"delicate\",\n \"flake\"\n ],\n \"finish_length\": 3,\n \"complexity\": 2.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Atlantic coast of France, especially Brittany, and select Mediterranean regions\"\n },\n \"season\": {\n \"en\": \"Summer\"\n },\n \"terroir_notes\": {\n \"en\": \"Profile reflects the mineral composition of local seawater and traditional hand-harvesting methods.\"\n }\n },\n \"notes\": {\n \"en\": \"Primarily used as a finishing salt due to its delicate texture and subtle, lingering minerality.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:fleur-de-sel", "expected": "ogs:core:ingredient:fleur-de-sel", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "salt", "expected": "salt", "match": true } } }, "metrics": { "input_tokens": 2514, "output_tokens": 464, "latency_ms": 3421.0, "usd": 0.00874, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:fleur-de-sel\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Fleur de sel\",\n \"category\": \"salt\",\n \"description\": \"A delicate, flaky sea salt hand-harvested from the surface of salt ponds, prized for its subtle mineral complexity and crisp, clean finish.\",\n \"primary_language\": \"en\",\n \"available_languages\": [\"en\", \"fr\"],\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 9,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 1,\n \"acidity_perception\": 0,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"sea spray\",\n \"item\": \"brine\",\n \"intensity\": 2\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"wet stone\",\n \"intensity\": 1\n }\n ],\n \"texture\": [\"crunchy\", \"delicate\", \"flake\"],\n \"finish_length\": 4,\n \"complexity\": 2\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Brittany, France\",\n \"fr\": \"Bretagne, France\"\n },\n \"season\": {\n \"en\": \"Summer (harvested May to September)\",\n \"fr\": \"Été (récolté de mai à septembre)\"\n },\n \"terroir_notes\": {\n \"en\": \"Distinctive mineral notes reflect the coastal environment and traditional hand-harvesting techniques of salt marshes.\",\n \"fr\": \"Notes minérales distinctes refletant l'environnement côtier et la récolte artisanale dans les marais salants.\"\n }\n },\n \"notes\": {\n \"en\": \"Used as a finishing salt to add texture and subtle salinity. Avoid exposing to heat to preserve delicate structure.\",\n \"fr\": \"Utilisé comme sel de finition pour sa texture et sa salinité subtile. À ne pas chauffer pour préserver sa structure délicate.\"\n },\n \"metadata\": {\n \"created\": \"2024-06-01T10:00:00Z\",\n \"updated\": \"2024-06-01T10:00:00Z\",\n \"source\": \"https://en.wikipedia.org/wiki/Fleur_de_sel\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:fleur-de-sel", "expected": "ogs:core:ingredient:fleur-de-sel", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "salt", "expected": "salt", "match": true } } }, "metrics": { "input_tokens": 2514, "output_tokens": 610, "latency_ms": 3937.3, "usd": 0.009908, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:fleur-de-sel\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Fleur de sel\",\n \"fr\": \"Fleur de sel\"\n },\n \"category\": \"salt\",\n \"description\": {\n \"en\": \"A delicate, flaky sea salt hand-harvested from the surface of evaporation ponds, known for its subtle saline flavor, soft texture, and mineral complexity.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 8.5,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 0.5,\n \"acidity_perception\": 0,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"sea air\",\n \"item\": \"briny\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"chalk\",\n \"intensity\": 1.0\n }\n ],\n \"texture\": [\n \"crunchy\",\n \"delicate\",\n \"flaky\",\n \"dissolves easily\"\n ],\n \"finish_length\": 2,\n \"complexity\": 3\n },\n \"origin\": {\n \"region\": {\n \"fr\": \"Côtes atlantiques françaises\",\n \"en\": \"French Atlantic coast\"\n },\n \"season\": {\n \"en\": \"Summer harvest\"\n },\n \"terroir_notes\": {\n \"en\": \"Mineral and saline nuances reflect the microclimate and traditional harvesting methods.\"\n }\n },\n \"notes\": {\n \"en\": \"Highly prized as a finishing salt for its texture and subtle flavor; not typically used in cooking.\"\n },\n \"metadata\": {\n \"created\": \"2024-06-26T00:00:00Z\",\n \"source\": \"OGS curation, French culinary tradition\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:fleur-de-sel", "expected": "ogs:core:ingredient:fleur-de-sel", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "salt", "expected": "salt", "match": true } } }, "metrics": { "input_tokens": 2514, "output_tokens": 510, "latency_ms": 3353.3, "usd": 0.009108, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2514.0, "output_tokens_mean": 528.0, "latency_ms_mean": 3570.533, "usd_sum": 0.027756 } }, { "task_id": "ogs:core:benchmark-task:struct-002", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "hard", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "367b58556573440d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing a Sancerre (Sauvignon Blanc, Loire Valley) that validates against the OGS beverage schema. Respond with ONLY the JSON object, no markdown fences.\n\nINPUT:\n{\n \"beverage_name\": \"Sancerre\",\n \"namespace\": \"core\",\n \"id_slug\": \"sancerre-generic\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:sancerre-generic", "ogs_version": "0.1.0", "type": "wine" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:sancerre-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Sancerre\",\n \"type\": \"wine\",\n \"subtype\": \"white\",\n \"grape_varieties\": [\n \"Sauvignon Blanc\"\n ],\n \"region\": \"Loire Valley\",\n \"appellation\": \"Sancerre\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 6.5,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 7,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 3.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"grapefruit\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"peach\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herbaceous\",\n \"item\": \"cut grass\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herbaceous\",\n \"item\": \"nettle\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"green\",\n \"item\": \"gooseberry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"flint\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"elderflower\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"crisp\",\n \"light-bodied\"\n ],\n \"finish_length\": 4,\n \"complexity\": 5.5\n },\n \"abv\": 12.5,\n \"serve_temperature_c\": {\n \"min\": 8,\n \"max\": 10\n },\n \"description\": \"A classic dry white wine from the Loire Valley, Sancerre is made from Sauvignon Blanc and renowned for its high acidity, fresh citrus and herbal aromas, and flinty minerality.\",\n \"producer\": \"\",\n \"metadata\": {}\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'' should be non-empty" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:sancerre-generic", "expected": "ogs:core:beverage:sancerre-generic", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "wine", "expected": "wine", "match": true } } }, "metrics": { "input_tokens": 2515, "output_tokens": 636, "latency_ms": 3725.6, "usd": 0.010118, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:sancerre-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Sancerre\",\n \"type\": \"wine\",\n \"grape_varieties\": [\n \"Sauvignon Blanc\"\n ],\n \"region\": \"Loire Valley\",\n \"appellation\": \"Sancerre\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 6.5,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3.5,\n \"acidity_perception\": 7,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 3.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"grapefruit\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"tree fruit\",\n \"item\": \"green apple\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"cut grass\",\n \"intensity\": 4\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herbaceous\",\n \"item\": \"nettle\",\n \"intensity\": 2\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"flint\",\n \"intensity\": 3\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"vegetal\",\n \"item\": \"asparagus\",\n \"intensity\": 1.5\n }\n ],\n \"texture\": [\n \"crisp\",\n \"light-bodied\"\n ],\n \"finish_length\": 5,\n \"complexity\": 4.5\n },\n \"serve_temperature_c\": {\n \"min\": 8,\n \"max\": 11\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:sancerre-generic", "expected": "ogs:core:beverage:sancerre-generic", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "wine", "expected": "wine", "match": true } } }, "metrics": { "input_tokens": 2515, "output_tokens": 506, "latency_ms": 3196.9, "usd": 0.009078, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:sancerre-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Sancerre\",\n \"type\": \"wine\",\n \"subtype\": \"white\",\n \"grape_varieties\": [\n \"Sauvignon Blanc\"\n ],\n \"region\": \"Loire Valley\",\n \"appellation\": \"Sancerre\",\n \"producer\": \"\",\n \"abv\": 13,\n \"serve_temperature_c\": {\n \"min\": 8,\n \"max\": 12\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 6.5,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0.5\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 7.5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 2.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"grapefruit\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"pome\",\n \"item\": \"green apple\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"cut grass\",\n \"intensity\": 7.5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"nettle\",\n \"intensity\": 6\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"elderflower\",\n \"intensity\": 4\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"flint\",\n \"intensity\": 5.5\n }\n ],\n \"texture\": [\n \"crisp\",\n \"light\",\n \"zippy\"\n ],\n \"finish_length\": 5.5,\n \"complexity\": 6\n },\n \"description\": \"A classic dry white wine from the Loire Valley, Sancerre is made from Sauvignon Blanc. It is noted for its zesty acidity, pronounced citrus, apple and herbal aromatics, flinty minerality, and fresh, crisp texture.\",\n \"metadata\": {\n \"source\": \"OGS Example / Loire typicity\",\n \"license\": \"CC-BY-SA 4.0\"\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'' should be non-empty" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:sancerre-generic", "expected": "ogs:core:beverage:sancerre-generic", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "wine", "expected": "wine", "match": true } } }, "metrics": { "input_tokens": 2515, "output_tokens": 608, "latency_ms": 4322.6, "usd": 0.009894, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": -0.32, "ci95_hi": 0.9867, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2515.0, "output_tokens_mean": 583.333, "latency_ms_mean": 3748.367, "usd_sum": 0.02909 } }, { "task_id": "ogs:core:benchmark-task:struct-003", "category": "structured_output", "capability": "schema_valid_pairing", "difficulty": "expert", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.pairing", "vocab.match_types", "vocab.explanation_codes", "vocab.grade_scale", "id.format", "ogs_version" ], "prompt_template_hash": "2740dc70d150e12a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS pairing schema (`schema/pairing.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/pairing.schema.json\",\n \"title\": \"OGS Pairing\",\n \"description\": \"A scored, explained pairing between a dish and a beverage.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"dish_ref\",\n \"beverage_ref\",\n \"match_types\",\n \"overall_score\",\n \"grade\",\n \"explanation_codes\",\n \"confidence\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:pairing:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"dish_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"beverage_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"match_types\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/match_type_entry\"\n }\n },\n \"overall_score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"grade\": {\n \"type\": \"string\",\n \"enum\": [\n \"A+\",\n \"A\",\n \"B+\",\n \"B\",\n \"C+\",\n \"C\",\n \"D\",\n \"F\"\n ]\n },\n \"explanation_codes\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/explanation_code_entry\"\n }\n },\n \"risks\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/risk_entry\"\n }\n },\n \"confidence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"evidence\": {\n \"$ref\": \"#/$defs/evidence\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"match_type_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"type\",\n \"score\"\n ],\n \"properties\": {\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"harmony\",\n \"contrast\",\n \"bridge\",\n \"intensity_alignment\",\n \"structural_balance\",\n \"refresh\"\n ]\n },\n \"score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"primary\": {\n \"type\": \"boolean\"\n }\n },\n \"additionalProperties\": false\n },\n \"explanation_code_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"weight\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"detail\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"risk_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\",\n \"severity\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"severity\": {\n \"type\": \"string\",\n \"enum\": [\n \"low\",\n \"medium\",\n \"high\"\n ]\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"mitigation\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"evidence\": {\n \"type\": \"object\",\n \"properties\": {\n \"method\": {\n \"type\": \"string\",\n \"enum\": [\n \"expert_panel\",\n \"instrumental\",\n \"computed\",\n \"estimated\"\n ]\n },\n \"sources\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n### OGS Explanation Codes\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS pairing JSON document for the described match. It MUST validate against the OGS pairing schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"pairing_slug\": \"brie-champagne\",\n \"dish_ref\": \"ogs:core:dish:brie-on-baguette\",\n \"beverage_ref\": \"ogs:core:beverage:brut-champagne-nv\",\n \"intent\": \"A classic refresh pairing driven by effervescence and acidity against creamy brie.\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/pairing.schema.json", "required_fields": { "id": "ogs:core:pairing:brie-champagne", "ogs_version": "0.1.0", "dish_ref": "ogs:core:dish:brie-on-baguette", "beverage_ref": "ogs:core:beverage:brut-champagne-nv" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie on Baguette with Brut Champagne NV\",\n \"dish_ref\": \"ogs:core:dish:brie-on-baguette\",\n \"beverage_ref\": \"ogs:core:beverage:brut-champagne-nv\",\n \"match_types\": [\n {\n \"type\": \"refresh\",\n \"score\": 93,\n \"description\": \"The effervescence and acidity of Brut Champagne refresh the palate between creamy bites of Brie, providing balance and lift.\",\n \"primary\": true\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 89,\n \"description\": \"Champagne's light to medium structure aligns well with the delicately creamy Brie and crisp baguette, so neither element is overwhelmed.\"\n }\n ],\n \"overall_score\": 92,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.5,\n \"detail\": \"Champagne's lively bubbles cleanse the palate of creamy Brie, preventing heaviness.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.2,\n \"detail\": \"High acidity in Champagne cuts through the richness of cheese, reinforcing refreshment.\"\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.2,\n \"detail\": \"Neither element overpowers the other; Champagne's body and Brie’s texture are balanced.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.1,\n \"detail\": \"Subtle yeasty, nutty, and lactic notes from cheese and Champagne create underlying harmony.\"\n }\n ],\n \"confidence\": 0.95,\n \"notes\": \"An iconic pairing, relying on Champagne's acid and effervescence to balance and refresh after each bite of Brie.\"\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:brie-champagne", "expected": "ogs:core:pairing:brie-champagne", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:brie-on-baguette", "expected": "ogs:core:dish:brie-on-baguette", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:brut-champagne-nv", "expected": "ogs:core:beverage:brut-champagne-nv", "match": true } } }, "metrics": { "input_tokens": 3380, "output_tokens": 449, "latency_ms": 3064.4, "usd": 0.010352, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie on Baguette with Brut Champagne NV\",\n \"dish_ref\": \"ogs:core:dish:brie-on-baguette\",\n \"beverage_ref\": \"ogs:core:beverage:brut-champagne-nv\",\n \"match_types\": [\n {\n \"type\": \"refresh\",\n \"score\": 92,\n \"description\": \"The pairing is led by the Champagne's effervescence and high acidity, which refresh the palate and cut through the creamy, rich brie cheese.\",\n \"primary\": true\n },\n {\n \"type\": \"harmony\",\n \"score\": 85,\n \"description\": \"Delicate flavors in both brie and Champagne yield a harmonious, subtle match.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 88,\n \"description\": \"The Champagne's acidity balances the richness and fat of the brie, supporting structural synergy.\"\n }\n ],\n \"overall_score\": 92,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.5,\n \"detail\": \"Champagne's bubbles physically cleanse the palate between bites of creamy brie.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.2,\n \"detail\": \"High acidity in the Champagne further refreshes and balances brie's richness.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.15,\n \"detail\": \"Delicate milky and bread notes in both the dish and beverage create harmony.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.15,\n \"detail\": \"Acidity from the Champagne masterfully cuts through and lifts the creamy texture of brie.\"\n }\n ],\n \"confidence\": 0.95,\n \"description\": \"A classic pairing: effervescent, high-acid Champagne refreshes and balances the creamy, rich brie, providing a clean, harmonious, palate-cleansing experience.\",\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"sources\": [\n \"K. MacNeil, 'The Wine Bible'\",\n \"Jancis Robinson, 'The Oxford Companion to Wine'\"\n ],\n \"notes\": \"A widely recommended combination in pairing literature for its refreshing and balanced character.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:brie-champagne", "expected": "ogs:core:pairing:brie-champagne", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:brie-on-baguette", "expected": "ogs:core:dish:brie-on-baguette", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:brut-champagne-nv", "expected": "ogs:core:beverage:brut-champagne-nv", "match": true } } }, "metrics": { "input_tokens": 3380, "output_tokens": 562, "latency_ms": 3680.6, "usd": 0.011256, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie on Baguette with Brut Champagne NV\",\n \"dish_ref\": \"ogs:core:dish:brie-on-baguette\",\n \"beverage_ref\": \"ogs:core:beverage:brut-champagne-nv\",\n \"match_types\": [\n {\n \"type\": \"refresh\",\n \"score\": 92,\n \"description\": \"The Champagne's lively effervescence and high acidity cut through the creamy, rich texture of the brie, providing a classic palate refresh.\",\n \"primary\": true\n },\n {\n \"type\": \"contrast\",\n \"score\": 86,\n \"description\": \"The crisp structure of Brut Champagne contrasts the rich, soft creaminess of brie.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 80,\n \"description\": \"Delicate flavors in both the Champagne and brie harmonize, allowing subtle dairy and yeasty notes to come together.\"\n }\n ],\n \"overall_score\": 91,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.5,\n \"detail\": \"Champagne's bubbles scrub the palate clean after each creamy bite.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.22,\n \"detail\": \"High acidity in Champagne balances the brie's richness.\"\n },\n {\n \"code\": \"CONTRAST_RICH_CRISP\",\n \"weight\": 0.14,\n \"detail\": \"The contrast of brie's richness with Champagne's crispness brings excitement.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.14,\n \"detail\": \"Subtle flavors (yeast, dairy, bread) echo and integrate.\"\n }\n ],\n \"confidence\": 0.97,\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"sources\": [\n \"Classic Pairings: Champagne and Soft Cheese, The Oxford Companion to Wine\",\n \"Cheese & Wine (2018), Patricia Michelson\"\n ],\n \"notes\": \"Widely recommended in gastronomy literature as a classic pairing.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:brie-champagne", "expected": "ogs:core:pairing:brie-champagne", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:brie-on-baguette", "expected": "ogs:core:dish:brie-on-baguette", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:brut-champagne-nv", "expected": "ogs:core:beverage:brut-champagne-nv", "match": true } } }, "metrics": { "input_tokens": 3380, "output_tokens": 520, "latency_ms": 3510.3, "usd": 0.01092, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3380.0, "output_tokens_mean": 510.333, "latency_ms_mean": 3418.433, "usd_sum": 0.032528 } }, { "task_id": "ogs:core:benchmark-task:struct-004", "category": "structured_output", "capability": "sensory_profile_json", "difficulty": "medium", "cuisine_region": "indian", "scorer": "json_match", "context_needs": [ "scales.basic_tastes", "scales.structural", "vocab.aromatic_families", "vocab.qualifiers" ], "prompt_template_hash": "9bd6860a8c5c69ec", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nProduce a JSON object representing the sensory profile for ripe mango. The object must have keys basic_tastes (with sweet, sour, salty, bitter, umami), structural (with body, acidity_perception, tannin, astringency, alcohol_heat, effervescence), and aromatics (array of entries with family, group, item, intensity). All intensities on 0-10. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"item\": \"ripe Alphonso mango, peak ripeness\"\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"object\",\n \"required\": [\n \"basic_tastes\",\n \"structural\",\n \"aromatics\"\n ],\n \"properties\": {\n \"basic_tastes\": {\n \"type\": \"object\",\n \"required\": [\n \"sweet\",\n \"sour\",\n \"salty\",\n \"bitter\",\n \"umami\"\n ]\n },\n \"structural\": {\n \"type\": \"object\",\n \"required\": [\n \"body\",\n \"acidity_perception\",\n \"tannin\",\n \"astringency\",\n \"alcohol_heat\",\n \"effervescence\"\n ]\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ]\n }\n }\n }\n}", "expected": { "value": { "basic_tastes": { "sweet": 8.5, "sour": 3.0, "salty": 0, "bitter": 0.5, "umami": 0.5 }, "structural": { "body": 5.5, "acidity_perception": 3.0, "tannin": 0, "astringency": 0.5, "alcohol_heat": 0, "effervescence": 0 } }, "required_keys": [ "basic_tastes.sweet", "basic_tastes.sour", "structural.body", "structural.acidity_perception", "structural.tannin" ] }, "samples": [ { "sample": 0, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 8,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 2.5,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"mango\",\n \"intensity\": 10\n },\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"pineapple\",\n \"intensity\": 3\n },\n {\n \"family\": \"floral\",\n \"group\": \"floral\",\n \"item\": \"jasmine\",\n \"intensity\": 2\n },\n {\n \"family\": \"confection\",\n \"group\": \"confection\",\n \"item\": \"candied\",\n \"intensity\": 2\n }\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2, "expected": 3.0, "match": true }, "structural.body": { "predicted": 6, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 713, "output_tokens": 263, "latency_ms": 1849.0, "usd": 0.00353, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 8.5,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"mango\",\n \"intensity\": 9\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone\",\n \"item\": \"apricot\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"floral\",\n \"item\": \"jasmine\",\n \"intensity\": 3\n },\n {\n \"family\": \"confection\",\n \"group\": \"candied\",\n \"item\": \"candied_fruit\",\n \"intensity\": 2\n }\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.5, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2, "expected": 3.0, "match": true }, "structural.body": { "predicted": 7, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 713, "output_tokens": 267, "latency_ms": 1797.8, "usd": 0.003562, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 8.5,\n \"sour\": 3.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 6.5,\n \"acidity_perception\": 3,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"mango\",\n \"intensity\": 9\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"apricot\",\n \"intensity\": 5\n },\n {\n \"family\": \"floral\",\n \"group\": \"floral\",\n \"item\": \"jasmine\",\n \"intensity\": 3\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"orange zest\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"candied\",\n \"item\": \"honey\",\n \"intensity\": 2\n }\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.5, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 3.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 6.5, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 3, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 713, "output_tokens": 310, "latency_ms": 2388.9, "usd": 0.003906, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 713.0, "output_tokens_mean": 280.0, "latency_ms_mean": 2011.9, "usd_sum": 0.010998 } }, { "task_id": "ogs:core:benchmark-task:struct-005", "category": "structured_output", "capability": "schema_valid_dish", "difficulty": "expert", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.dish", "vocab.component_roles", "vocab.cooking_methods", "vocab.courses", "vocab.service_temperatures", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "9caf9bc474b2464d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS dish schema (`schema/dish.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/dish.schema.json\",\n \"title\": \"OGS Dish\",\n \"description\": \"A composed dish with components, cooking methods, and overall sensory profile.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"components\",\n \"overall_sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"cuisine\": {\n \"type\": \"string\",\n \"description\": \"Free-text cuisine name (v0.1) OR a cuisine entity reference matching ogs::cuisine: (v0.2+).\"\n },\n \"course\": {\n \"type\": \"string\",\n \"enum\": [\n \"amuse\",\n \"appetizer\",\n \"soup\",\n \"salad\",\n \"fish\",\n \"main\",\n \"cheese\",\n \"dessert\",\n \"petit_four\"\n ]\n },\n \"service_temperature\": {\n \"type\": \"string\",\n \"enum\": [\n \"frozen\",\n \"cold\",\n \"cool\",\n \"room\",\n \"warm\",\n \"hot\",\n \"very_hot\"\n ]\n },\n \"components\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/component\"\n }\n },\n \"overall_sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"component\": {\n \"type\": \"object\",\n \"required\": [\n \"role\",\n \"ingredient_ref\"\n ],\n \"properties\": {\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"main_protein\",\n \"main_vegetable\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n ]\n },\n \"ingredient_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\"\n },\n \"cooking_method\": {\n \"type\": \"string\",\n \"enum\": [\n \"raw\",\n \"seared\",\n \"grilled\",\n \"roasted\",\n \"braised\",\n \"poached\",\n \"steamed\",\n \"fried\",\n \"confit\",\n \"smoked\",\n \"fermented\",\n \"cured\",\n \"pickled\",\n \"dehydrated\",\n \"sous_vide\",\n \"blanched\",\n \"sauteed\",\n \"baked\",\n \"charred\",\n \"emulsified\"\n ]\n },\n \"maillard_index\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"reduction_level\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"proportion\": {\n \"type\": \"string\",\n \"enum\": [\n \"dominant\",\n \"significant\",\n \"accent\",\n \"trace\"\n ]\n },\n \"sensory_contribution\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS dish JSON document for 'moules marinieres' (mussels steamed with white wine, shallots, parsley, butter). It must validate against the OGS dish schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"dish_slug\": \"moules-marinieres\",\n \"cuisine\": \"french\",\n \"course\": \"main\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/dish.schema.json", "required_fields": { "id": "ogs:core:dish:moules-marinieres", "ogs_version": "0.1.0" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Moules Marinières\",\n \"fr\": \"Moules marinières\"\n },\n \"cuisine\": \"french\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:mussel\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 4,\n \"bitter\": 0,\n \"umami\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\"tender\", \"juicy\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\"soft\"]\n }\n },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"reduction\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 3,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"grape\",\n \"item\": \"white wine\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n }\n ],\n \"texture\": []\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 1,\n \"bitter\": 0,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\"rich\", \"creamy\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\"fresh\"]\n }\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:salt\",\n \"proportion\": \"trace\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:black-pepper\",\n \"proportion\": \"trace\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 2.5,\n \"salty\": 4,\n \"bitter\": 0.5,\n \"umami\": 5\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 3,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 2\n },\n {\n \"family\": \"fruit\",\n \"group\": \"grape\",\n \"item\": \"white wine\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\"tender\", \"juicy\", \"creamy\", \"fresh\"],\n \"finish_length\": 4,\n \"complexity\": 6\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'reduction' is not one of ['raw', 'seared', 'grilled', 'roasted', 'braised', 'poached', 'steamed', 'fried', 'confit', 'smoked', 'fermented', 'cured', 'pickled', 'dehydrated', 'sous_vide', 'blanched', 'sauteed', 'baked', 'charred', 'emulsified']" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:moules-marinieres", "expected": "ogs:core:dish:moules-marinieres", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 3080, "output_tokens": 1340, "latency_ms": 6453.5, "usd": 0.01688, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Moules Marinières\",\n \"fr\": \"Moules marinières\"\n },\n \"description\": {\n \"en\": \"Classic French dish of mussels steamed with white wine, shallots, parsley, and butter.\"\n },\n \"cuisine\": \"french\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:mussel\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 2,\n \"salty\": 3,\n \"bitter\": 0,\n \"umami\": 6\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\"tender\", \"juicy\"]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 3,\n \"salty\": 0.5,\n \"bitter\": 0,\n \"umami\": 0.5\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"white_fruit\",\n \"item\": \"grape\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\"liquid\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 2.5\n }\n ],\n \"texture\": [\"soft\"]\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 1,\n \"bitter\": 0,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\"creamy\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"trace\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy_herb\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 1.5\n }\n ],\n \"texture\": [\"fresh\"]\n }\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:fleur-de-sel\",\n \"proportion\": \"trace\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 1,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"aromatics\": [],\n \"texture\": []\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 2.5,\n \"salty\": 3,\n \"bitter\": 0.2,\n \"umami\": 6\n },\n \"structural\": {\n \"body\": 4.5,\n \"acidity_perception\": 3,\n \"tannin\": 0,\n \"astringency\": 0.2,\n \"alcohol_heat\": 0.2,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"white_fruit\",\n \"item\": \"grape\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 1.5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"leafy_herb\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 1\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"qualifier\": \"fresh\",\n \"intensity\": 1\n }\n ],\n \"texture\": [\n \"tender\",\n \"juicy\",\n \"creamy\",\n \"fresh\"\n ],\n \"finish_length\": 4.5,\n \"complexity\": 5\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:moules-marinieres", "expected": "ogs:core:dish:moules-marinieres", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 3080, "output_tokens": 1473, "latency_ms": 7982.1, "usd": 0.017944, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Moules Marinières\",\n \"fr\": \"Moules marinières\"\n },\n \"cuisine\": \"french\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:mussels\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 2,\n \"bitter\": 0,\n \"umami\": 4\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\n \"tender\",\n \"juicy\"\n ]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"white_wine\",\n \"item\": \"green apple\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"brothy\",\n \"light\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"soft\"\n ]\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 0.5,\n \"bitter\": 0,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"fresh butter\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"silky\",\n \"rich\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"fresh\",\n \"light\"\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 1.2,\n \"salty\": 2,\n \"bitter\": 0.5,\n \"umami\": 5\n },\n \"structural\": {\n \"body\": 4.5,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 0.2,\n \"alcohol_heat\": 0.3,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 1.5\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"fresh butter\",\n \"intensity\": 2\n },\n {\n \"family\": \"fruit\",\n \"group\": \"white_wine\",\n \"item\": \"green apple\",\n \"qualifier\": \"fresh\",\n \"intensity\": 1\n }\n ],\n \"texture\": [\n \"tender\",\n \"juicy\",\n \"brothy\",\n \"silky\"\n ],\n \"finish_length\": 6,\n \"complexity\": 5\n },\n \"description\": {\n \"en\": \"Classic French dish of mussels steamed with white wine, shallots, parsley, and butter. Served hot with a fragrant, brothy sauce.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:moules-marinieres", "expected": "ogs:core:dish:moules-marinieres", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 3080, "output_tokens": 1383, "latency_ms": 8318.9, "usd": 0.017224, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": 0.0133, "ci95_hi": 1.32, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3080.0, "output_tokens_mean": 1398.667, "latency_ms_mean": 7584.833, "usd_sum": 0.052048 } }, { "task_id": "ogs:core:benchmark-task:struct-006", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "medium", "cuisine_region": "iranian", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "bb4d0fcee2d1e751", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'saffron' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"saffron\",\n \"namespace\": \"core\",\n \"id_slug\": \"saffron-stigma\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:saffron-stigma", "ogs_version": "0.1.0", "category": "spice" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:saffron-stigma\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"saffron\",\n \"category\": \"spice\",\n \"description\": \"The dried stigmas of Crocus sativus flowers, prized for their unique aroma, golden color, and flavoring qualities.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 3.5,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 2.5,\n \"acidity_perception\": 0,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"spice\",\n \"item\": \"saffron\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"floral\",\n \"item\": \"hay\",\n \"qualifier\": \"dried\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"earthy\",\n \"item\": \"earthy\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\"dry\", \"papery\"],\n \"finish_length\": 7,\n \"complexity\": 8\n },\n \"origin\": {\n \"region\": \"Iran, India, Mediterranean\",\n \"season\": \"Autumn harvest\",\n \"terroir_notes\": \"Quality and aroma most pronounced from regions with hot, dry summers and well-drained soils.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:saffron-stigma", "expected": "ogs:core:ingredient:saffron-stigma", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2502, "output_tokens": 408, "latency_ms": 3274.1, "usd": 0.008268, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:saffron-stigma\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"saffron\",\n \"category\": \"spice\",\n \"description\": \"The dried red stigmas of Crocus sativus flower, used for its distinctive color, aroma, and flavor in cuisines worldwide.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 2.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 1,\n \"acidity_perception\": 0,\n \"tannin\": 0.5,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"warm spice\",\n \"item\": \"saffron\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"rich floral\",\n \"item\": \"honeyed flowers\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"hay\",\n \"item\": \"dry hay\",\n \"intensity\": 3.5,\n \"qualifier\": \"dried\"\n }\n ],\n \"texture\": [\n \"papery\",\n \"filamentous (when whole)\"\n ],\n \"finish_length\": 6,\n \"complexity\": 7\n },\n \"origin\": {\n \"region\": \"Mediterranean, Middle East, South Asia\",\n \"season\": \"Autumn (harvest)\",\n \"terroir_notes\": \"Quality and aromatic profile vary with altitude, soil drainage, and climate; regions like Iran, Spain, and Kashmir are renowned for distinctive terroir-driven nuances.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:saffron-stigma", "expected": "ogs:core:ingredient:saffron-stigma", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2502, "output_tokens": 442, "latency_ms": 3332.3, "usd": 0.00854, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:saffron-stigma\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"saffron\",\n \"category\": \"spice\",\n \"description\": \"The dried stigmas of Crocus sativus, prized for their unique flavor, aroma, and vivid golden color.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 0.5,\n \"salty\": 0,\n \"bitter\": 2.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 1,\n \"acidity_perception\": 0.5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"warm spice\",\n \"item\": \"saffron\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"exotic flower\",\n \"item\": \"honeyed\",\n \"intensity\": 5\n },\n {\n \"family\": \"earth\",\n \"group\": \"hay\",\n \"item\": \"dry hay\",\n \"intensity\": 4.5\n }\n ],\n \"texture\": [\n \"dry\",\n \"papery\"\n ],\n \"finish_length\": 5.5,\n \"complexity\": 7\n },\n \"origin\": {\n \"region\": \"Iran, Kashmir, Spain, Mediterranean basin\",\n \"season\": \"Harvested in autumn\",\n \"terroir_notes\": \"Soil, climate, and hand-harvesting practices influence aroma intensity and color.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:saffron-stigma", "expected": "ogs:core:ingredient:saffron-stigma", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2502, "output_tokens": 415, "latency_ms": 3711.5, "usd": 0.008324, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2502.0, "output_tokens_mean": 421.667, "latency_ms_mean": 3439.3, "usd_sum": 0.025132 } }, { "task_id": "ogs:core:benchmark-task:struct-007", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "0bc2e49ee6c1093e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'miso (red)' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"miso (red)\",\n \"namespace\": \"core\",\n \"id_slug\": \"aka-miso\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:aka-miso", "ogs_version": "0.1.0", "category": "other" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"miso (red)\",\n \"category\": \"fermented\",\n \"description\": \"A red, long-fermented miso paste made from soybeans, salt, and koji, known for its intense flavor, pronounced umami, and deep reddish-brown color.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 2,\n \"salty\": 7.5,\n \"bitter\": 1.5,\n \"umami\": 9\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 2,\n \"tannin\": 0.5,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy sauce\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"fermented bean\",\n \"item\": \"soybean\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"spice\",\n \"group\": \"umami-rich\",\n \"item\": \"nutty\",\n \"intensity\": 4\n },\n {\n \"family\": \"dairy\",\n \"group\": \"fermented\",\n \"item\": \"cheese rind\",\n \"intensity\": 3\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramelized\",\n \"item\": \"molasses\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"paste\",\n \"grainy\",\n \"spreadable\",\n \"sticky\"\n ],\n \"finish_length\": 8,\n \"complexity\": 8.5\n },\n \"origin\": {\n \"region\": \"Japan\",\n \"season\": \"year-round\"\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'fermented' is not one of ['protein', 'vegetable', 'fruit', 'grain', 'dairy', 'fat', 'herb', 'spice', 'fungus', 'legume', 'nut', 'seed', 'sweetener', 'acid', 'salt', 'other']" ], "consistent": false, "required_fields": { "id": { "predicted": "ogs:core:ingredient:aka-miso", "expected": "ogs:core:ingredient:aka-miso", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fermented", "expected": "other", "match": false } } }, "metrics": { "input_tokens": 2502, "output_tokens": 472, "latency_ms": 3610.6, "usd": 0.00878, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"miso (red)\",\n \"category\": \"fermented\",\n \"description\": \"A fermented Japanese seasoning paste made primarily from soybeans and rice or barley, with a higher proportion of soy and longer fermentation time compared to white miso, resulting in a deeper color and more intense, savory flavor.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 2,\n \"salty\": 8,\n \"bitter\": 2.5,\n \"umami\": 9\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 2,\n \"tannin\": 1,\n \"astringency\": 1.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"fungal\",\n \"item\": \"mushroom\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"group\": \"nutty\",\n \"item\": \"toasted nuts\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"dairy\",\n \"group\": \"fermented\",\n \"item\": \"cheese rind\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"thick paste\",\n \"grainy\",\n \"sticky\"\n ],\n \"finish_length\": 7,\n \"complexity\": 8\n },\n \"origin\": {\n \"region\": \"Japan\",\n \"season\": \"Year-round\",\n \"terroir_notes\": \"Usually made in regions known for traditional miso culture, sometimes using local grains or water.\"\n },\n \"notes\": \"Red miso (aka miso) is more pungent and salty than white miso, often used for hearty soups, marinades, and braises.\",\n \"metadata\": {\n \"created\": \"2024-06-20T00:00:00Z\",\n \"updated\": \"2024-06-20T00:00:00Z\",\n \"source\": \"OGS core ingredient reference, standard sensory evaluation\",\n \"license\": \"CC BY-SA 4.0\"\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'fermented' is not one of ['protein', 'vegetable', 'fruit', 'grain', 'dairy', 'fat', 'herb', 'spice', 'fungus', 'legume', 'nut', 'seed', 'sweetener', 'acid', 'salt', 'other']" ], "consistent": false, "required_fields": { "id": { "predicted": "ogs:core:ingredient:aka-miso", "expected": "ogs:core:ingredient:aka-miso", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fermented", "expected": "other", "match": false } } }, "metrics": { "input_tokens": 2502, "output_tokens": 568, "latency_ms": 3969.1, "usd": 0.009548, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"miso (red)\",\n \"category\": \"fermented\",\n \"description\": {\n \"en\": \"A Japanese fermented soybean paste known as red miso (aka miso), characterized by its strong, savory, umami-rich profile, reddish brown color, long fermentation, and deep, complex flavors. Used in soups, marinades, and sauces.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 2.5,\n \"salty\": 7.5,\n \"bitter\": 3,\n \"umami\": 8.5\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 3,\n \"tannin\": 0.5,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"fermentation\",\n \"item\": \"umami paste\",\n \"intensity\": 8\n },\n {\n \"family\": \"spice\",\n \"group\": \"yeast\",\n \"item\": \"miso\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"thick\",\n \"smooth\",\n \"paste-like\"\n ],\n \"finish_length\": 7,\n \"complexity\": 8\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Japan\"\n },\n \"season\": {\n \"en\": \"Available year-round\"\n },\n \"terroir_notes\": {\n \"en\": \"Flavor intensity and complexity vary with region, fermentation length, and soy/rice ratio.\"\n }\n },\n \"notes\": {\n \"en\": \"Red miso is saltier and more robust than white (shiro) miso. A staple in Japanese cuisine.\"\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'fermented' is not one of ['protein', 'vegetable', 'fruit', 'grain', 'dairy', 'fat', 'herb', 'spice', 'fungus', 'legume', 'nut', 'seed', 'sweetener', 'acid', 'salt', 'other']" ], "consistent": false, "required_fields": { "id": { "predicted": "ogs:core:ingredient:aka-miso", "expected": "ogs:core:ingredient:aka-miso", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fermented", "expected": "other", "match": false } } }, "metrics": { "input_tokens": 2502, "output_tokens": 494, "latency_ms": 3358.5, "usd": 0.008956, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2502.0, "output_tokens_mean": 511.333, "latency_ms_mean": 3646.067, "usd_sum": 0.027284 } }, { "task_id": "ogs:core:benchmark-task:struct-008", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "hard", "cuisine_region": "turkish", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "791ac1beebd95233", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'Urfa chili' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"Urfa chili\",\n \"namespace\": \"core\",\n \"id_slug\": \"urfa-biber\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:urfa-biber", "ogs_version": "0.1.0", "category": "spice" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Urfa chili\",\n \"category\": \"spice\",\n \"description\": \"A Turkish dried chili pepper with a deep maroon color, noted for its smoky, raisiny, and chocolate-like flavors, moderate heat, and oily texture.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 0.5,\n \"bitter\": 2,\n \"umami\": 4\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 1,\n \"tannin\": 1.5,\n \"astringency\": 2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"chili\",\n \"item\": \"dried chili\",\n \"intensity\": 6,\n \"qualifier\": \"dried\"\n },\n {\n \"family\": \"earth\",\n \"group\": \"smoke\",\n \"item\": \"smoky\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"intensity\": 4,\n \"qualifier\": \"dried\"\n },\n {\n \"family\": \"confection\",\n \"group\": \"cocoa\",\n \"item\": \"dark chocolate\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"oily\",\n \"coarse\",\n \"slightly chewy\"\n ],\n \"finish_length\": 5,\n \"complexity\": 6\n },\n \"origin\": {\n \"region\": \"Şanlıurfa, Turkey\",\n \"season\": \"summer to autumn\"\n },\n \"notes\": \"Also known as Isot pepper. Used for its unique balance of gentle heat and deep, sweet-smoky flavor.\",\n \"metadata\": {\n \"created\": \"2024-06-11T00:00:00Z\",\n \"source\": \"OGS core ingredient, expert description\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:urfa-biber", "expected": "ogs:core:ingredient:urfa-biber", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 513, "latency_ms": 4184.8, "usd": 0.009106, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Urfa chili\",\n \"tr\": \"Urfa biber\"\n },\n \"category\": \"spice\",\n \"description\": {\n \"en\": \"A dried, coarsely ground chili pepper from the Urfa region of Turkey, known for its deep burgundy color, oily texture, moderate heat, and complex aromatic character with notes of raisin, tobacco, and chocolate.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 1,\n \"salty\": 1,\n \"bitter\": 2,\n \"umami\": 2.5\n },\n \"structural\": {\n \"body\": 4.5,\n \"acidity_perception\": 1,\n \"tannin\": 0.5,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"pepper\",\n \"item\": \"chili\",\n \"qualifier\": \"dried\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"smoky\",\n \"item\": \"tobacco\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"chocolate\",\n \"item\": \"dark chocolate\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"oily\",\n \"coarse\",\n \"moist\"\n ],\n \"finish_length\": 5,\n \"complexity\": 5.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Urfa (Şanlıurfa), Turkey\"\n },\n \"season\": {\n \"en\": \"harvested late summer, sun-dried and processed with oil and salt\"\n },\n \"terroir_notes\": {\n \"en\": \"Arid climate with hot days and cool nights, lending a distinctive depth, mild heat, and raisin-like sweetness.\"\n }\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:urfa-biber", "expected": "ogs:core:ingredient:urfa-biber", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 549, "latency_ms": 4204.4, "usd": 0.009394, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Urfa chili\",\n \"category\": \"spice\",\n \"description\": \"A dried Turkish chili pepper from the Urfa region, known for its deep maroon color and complex savory, smoky, earthy, and fruity aroma. It has moderate heat and a characteristic oily texture.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 1,\n \"bitter\": 2.5,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 4,\n \"acidity_perception\": 1,\n \"tannin\": 1,\n \"astringency\": 2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"pepper\",\n \"item\": \"chili\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"earthy\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried\",\n \"item\": \"raisin\",\n \"qualifier\": \"dried\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"smoke\",\n \"group\": \"savory\",\n \"item\": \"smoky\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"savory\",\n \"group\": \"umami\",\n \"item\": \"meaty\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"oily\",\n \"moist\",\n \"coarse\"\n ],\n \"finish_length\": 4.5,\n \"complexity\": 5.5\n },\n \"origin\": {\n \"region\": \"Şanlıurfa, Turkey\",\n \"season\": \"Late summer to early autumn\",\n \"terroir_notes\": \"Warm semi-arid climate; peppers are sun-dried and wrapped at night for partial fermentation.\"\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'smoke' is not one of ['fruit', 'floral', 'herbal', 'spice', 'earth', 'wood', 'dairy', 'savory', 'confection', 'vegetal', 'marine']" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:urfa-biber", "expected": "ogs:core:ingredient:urfa-biber", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 511, "latency_ms": 3089.5, "usd": 0.00909, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": 0.0133, "ci95_hi": 1.32, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2501.0, "output_tokens_mean": 524.333, "latency_ms_mean": 3826.233, "usd_sum": 0.02759 } }, { "task_id": "ogs:core:benchmark-task:struct-009", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "easy", "cuisine_region": "american", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "a6a51cef64e43626", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'Meyer lemon' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"Meyer lemon\",\n \"namespace\": \"core\",\n \"id_slug\": \"meyer-lemon\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:meyer-lemon", "ogs_version": "0.1.0", "category": "fruit" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:meyer-lemon\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Meyer lemon\",\n \"category\": \"fruit\",\n \"description\": \"A hybrid citrus fruit between a mandarin/pomelo and a lemon, known for its sweeter, floral, and less acidic flavor compared to regular lemons.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 5.5,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 6,\n \"tannin\": 0,\n \"astringency\": 2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"mandarin orange\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"blossom\",\n \"item\": \"honeysuckle\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"juicy\",\n \"tender pulp\",\n \"thin-skinned\"\n ],\n \"finish_length\": 4.5,\n \"complexity\": 5\n },\n \"origin\": {\n \"region\": \"China\",\n \"season\": \"Late fall to early spring\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:meyer-lemon", "expected": "ogs:core:ingredient:meyer-lemon", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fruit", "expected": "fruit", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 402, "latency_ms": 2310.0, "usd": 0.008218, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:meyer-lemon\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Meyer lemon\",\n \"category\": \"fruit\",\n \"description\": \"A hybrid citrus fruit known for its sweet, floral, and less acidic character compared to regular lemons, with a thin, deep yellow to orange skin.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 5,\n \"sour\": 6.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 4,\n \"acidity_perception\": 6.5,\n \"tannin\": 0,\n \"astringency\": 2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 8\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"mandarin orange\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"citrus flower\",\n \"item\": \"orange blossom\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"juicy\",\n \"tender\",\n \"thin-skinned\"\n ],\n \"finish_length\": 4,\n \"complexity\": 6\n },\n \"origin\": {\n \"region\": \"China\",\n \"season\": \"Winter to early spring\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:meyer-lemon", "expected": "ogs:core:ingredient:meyer-lemon", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fruit", "expected": "fruit", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 404, "latency_ms": 2760.3, "usd": 0.008234, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:meyer-lemon\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Meyer lemon\",\n \"category\": \"fruit\",\n \"description\": \"A hybrid citrus fruit, rounder and softer than common lemons, with a fragrant, sweet-tart flavor and floral aroma.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 5.5,\n \"sour\": 5.5,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3.5,\n \"acidity_perception\": 6,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"mandarin orange\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"blossom\",\n \"item\": \"honeysuckle\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"juicy\",\n \"tender pulp\",\n \"thin skin\"\n ],\n \"finish_length\": 4.5,\n \"complexity\": 5.5\n },\n \"origin\": {\n \"region\": \"China\",\n \"season\": \"Winter to early spring\",\n \"terroir_notes\": \"Best flavor develops in subtropical climates with cool nights.\"\n },\n \"notes\": \"Meyer lemon is prized in culinary uses for its sweeter, less acidic taste and floral aroma compared to common lemons.\",\n \"metadata\": {\n \"created\": \"2024-06-22T00:00:00Z\",\n \"source\": \"OGS Expert Panel\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:meyer-lemon", "expected": "ogs:core:ingredient:meyer-lemon", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fruit", "expected": "fruit", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 488, "latency_ms": 3342.2, "usd": 0.008906, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2501.0, "output_tokens_mean": 431.333, "latency_ms_mean": 2804.167, "usd_sum": 0.025358 } }, { "task_id": "ogs:core:benchmark-task:struct-010", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "hard", "cuisine_region": "mexican", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "6d4d6d3cc23f3283", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'wild huitlacoche' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"wild huitlacoche\",\n \"namespace\": \"core\",\n \"id_slug\": \"huitlacoche\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:huitlacoche", "ogs_version": "0.1.0", "category": "fungus" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"wild huitlacoche\",\n \"es\": \"huitlacoche silvestre\"\n },\n \"category\": \"fungus\",\n \"description\": {\n \"en\": \"Wild huitlacoche, also known as corn smut, is a fungus that grows naturally on maize. Prized in Mexican cuisine, it has a rich, earthy flavor profile with savory, mushroom-like notes and subtle sweetness.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 0.5,\n \"salty\": 0,\n \"bitter\": 2,\n \"umami\": 6.5\n },\n \"structural\": {\n \"body\": 5.5,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"fungal\",\n \"item\": \"mushroom\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"fresh corn\",\n \"intensity\": 2\n },\n {\n \"family\": \"savory\",\n \"group\": \"umami\",\n \"item\": \"broth\",\n \"intensity\": 4.5\n }\n ],\n \"texture\": [\n \"velvety\",\n \"tender\",\n \"slightly pasty\"\n ],\n \"finish_length\": 5,\n \"complexity\": 6\n },\n \"origin\": {\n \"region\": {\n \"es\": \"México\",\n \"en\": \"Mexico\"\n },\n \"season\": {\n \"en\": \"June to September (rainy season in corn fields)\"\n },\n \"terroir_notes\": {\n \"en\": \"Grows wild on maize during humid periods; flavor influenced by corn variety and growing conditions.\"\n }\n },\n \"notes\": {\n \"en\": \"Also called 'corn truffle' or 'Mexican truffle'. Traditionally harvested from wild cornfields. Used in quesadillas, soups, and tamales.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:huitlacoche", "expected": "ogs:core:ingredient:huitlacoche", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fungus", "expected": "fungus", "match": true } } }, "metrics": { "input_tokens": 2503, "output_tokens": 546, "latency_ms": 4193.8, "usd": 0.009374, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"wild huitlacoche\",\n \"es\": \"huitlacoche silvestre\"\n },\n \"category\": \"fungus\",\n \"description\": {\n \"en\": \"Wild huitlacoche (Ustilago maydis) is a naturally occurring edible fungus that grows on corn kernels, forming irregular blackish-grey galls. It is prized in Mexican cuisine for its earthy, savory, and umami-rich flavor, with hints of corn, mushroom, and truffle.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 2.5,\n \"umami\": 7.5\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"truffle\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"fresh corn\",\n \"intensity\": 4\n },\n {\n \"family\": \"savory\",\n \"group\": \"umami\",\n \"item\": \"yeast\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"wet earth\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"soft\",\n \"moist\",\n \"creamy\",\n \"crumbly\"\n ],\n \"finish_length\": 5.5,\n \"complexity\": 7\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Central and Southern Mexico\"\n },\n \"season\": {\n \"en\": \"Rainy season (June–September)\"\n },\n \"terroir_notes\": {\n \"en\": \"Thrives in traditional cornfields exposed to summer rains; wild specimens may reflect local corn varieties and field conditions.\"\n }\n },\n \"notes\": {\n \"en\": \"Also called 'corn smut' or 'Mexican truffle'; typically foraged but can be cultivated, with wild forms having more pronounced earthiness and depth.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:huitlacoche", "expected": "ogs:core:ingredient:huitlacoche", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fungus", "expected": "fungus", "match": true } } }, "metrics": { "input_tokens": 2503, "output_tokens": 582, "latency_ms": 4163.1, "usd": 0.009662, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"wild huitlacoche\",\n \"es\": \"huitlacoche silvestre\"\n },\n \"category\": \"fungus\",\n \"description\": {\n \"en\": \"Wild huitlacoche, also known as corn smut, is a maize fungus prized in Mexican cuisine for its unique earthy and savory flavors.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 7\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"truffle\",\n \"intensity\": 7\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"fresh corn\",\n \"intensity\": 5\n },\n {\n \"family\": \"savory\",\n \"group\": \"umami\",\n \"item\": \"soy\",\n \"intensity\": 3\n },\n {\n \"family\": \"wood\",\n \"group\": \"smoke\",\n \"item\": \"wet wood\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"soft\",\n \"moist\",\n \"creamy\",\n \"crumbly\"\n ],\n \"finish_length\": 6,\n \"complexity\": 6\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Central Mexico\"\n },\n \"season\": {\n \"en\": \"summer rainy season\"\n },\n \"terroir_notes\": {\n \"en\": \"Grows on maize ears exposed to humid, rainy fields, with flavor nuances depending on soil richness and corn variety.\"\n }\n },\n \"notes\": {\n \"en\": \"Considered a delicacy in Mexican cuisine; sometimes called 'Mexican truffle'. Used in quesadillas, tamales, and soups.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:huitlacoche", "expected": "ogs:core:ingredient:huitlacoche", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "fungus", "expected": "fungus", "match": true } } }, "metrics": { "input_tokens": 2503, "output_tokens": 533, "latency_ms": 4340.1, "usd": 0.00927, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2503.0, "output_tokens_mean": 553.667, "latency_ms_mean": 4232.333, "usd_sum": 0.028306 } }, { "task_id": "ogs:core:benchmark-task:struct-011", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "medium", "cuisine_region": "italian", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "6615664480900680", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing 'Barolo' as an OGS beverage. It MUST validate against the OGS beverage schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"beverage_name\": \"Barolo\",\n \"namespace\": \"core\",\n \"id_slug\": \"barolo-docg\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:barolo-docg", "ogs_version": "0.1.0", "type": "wine" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Barolo\",\n \"type\": \"wine\",\n \"subtype\": \"red wine\",\n \"region\": \"Piedmont, Italy\",\n \"appellation\": \"Barolo DOCG\",\n \"grape_varieties\": [\"Nebbiolo\"],\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 4.5,\n \"salty\": 0,\n \"bitter\": 3.5,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 6.5,\n \"acidity_perception\": 6.5,\n \"tannin\": 8.5,\n \"astringency\": 8,\n \"alcohol_heat\": 6.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"cherry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"raspberry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"rose\",\n \"item\": \"rose petal\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"licorice\",\n \"intensity\": 2\n },\n {\n \"family\": \"earth\",\n \"group\": \"truffle\",\n \"item\": \"truffle\",\n \"intensity\": 2\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"cedar\",\n \"intensity\": 2\n },\n {\n \"family\": \"herbal\",\n \"group\": \"dried herbs\",\n \"item\": \"fennel\",\n \"intensity\": 1\n },\n {\n \"family\": \"spice\",\n \"group\": \"spice\",\n \"item\": \"tar\",\n \"intensity\": 2.5\n }\n ],\n \"texture\": [\"grippy\", \"velvety\", \"firm\"],\n \"finish_length\": 8,\n \"complexity\": 8\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:barolo-docg", "expected": "ogs:core:beverage:barolo-docg", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "wine", "expected": "wine", "match": true } } }, "metrics": { "input_tokens": 2507, "output_tokens": 578, "latency_ms": 3978.6, "usd": 0.009638, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Barolo\"\n },\n \"type\": \"wine\",\n \"subtype\": \"red wine\",\n \"grape_varieties\": [\n \"Nebbiolo\"\n ],\n \"region\": {\n \"en\": \"Piedmont\"\n },\n \"appellation\": {\n \"en\": \"Barolo DOCG\"\n },\n \"producer\": {},\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 4.5,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 6,\n \"tannin\": 8,\n \"astringency\": 7,\n \"alcohol_heat\": 7,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"cherry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"raspberry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"rose\",\n \"item\": \"rose\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"spice\",\n \"group\": \"spice\",\n \"item\": \"licorice\",\n \"intensity\": 3\n },\n {\n \"family\": \"earth\",\n \"group\": \"truffle\",\n \"item\": \"truffle\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"cedar\",\n \"intensity\": 2\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herb\",\n \"item\": \"dried herbs\",\n \"qualifier\": \"dried\",\n \"intensity\": 2\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"prune\",\n \"qualifier\": \"dried\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"structured\",\n \"dry\",\n \"firm tannin\"\n ],\n \"finish_length\": 8,\n \"complexity\": 8.5\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "{} is not valid under any of the given schemas" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:barolo-docg", "expected": "ogs:core:beverage:barolo-docg", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "wine", "expected": "wine", "match": true } } }, "metrics": { "input_tokens": 2507, "output_tokens": 616, "latency_ms": 3330.7, "usd": 0.009942, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Barolo\"\n },\n \"type\": \"wine\",\n \"subtype\": \"red\",\n \"grape_varieties\": [\n \"Nebbiolo\"\n ],\n \"region\": {\n \"en\": \"Piedmont, Italy\"\n },\n \"appellation\": {\n \"en\": \"Barolo DOCG\"\n },\n \"producer\": {},\n \"abv\": 14.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 4.5,\n \"salty\": 0,\n \"bitter\": 2.5,\n \"umami\": 1.5\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 5.5,\n \"tannin\": 8,\n \"astringency\": 7.5,\n \"alcohol_heat\": 6.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"cherry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"plum\",\n \"qualifier\": \"dried\",\n \"intensity\": 2\n },\n {\n \"family\": \"floral\",\n \"group\": \"rose\",\n \"item\": \"rose\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"spice\",\n \"group\": \"spices\",\n \"item\": \"licorice\",\n \"intensity\": 2\n },\n {\n \"family\": \"earth\",\n \"group\": \"truffle\",\n \"item\": \"truffle\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"cedar\",\n \"intensity\": 2\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herbs\",\n \"item\": \"tar\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"firm\",\n \"grippy\",\n \"velvety\"\n ],\n \"finish_length\": 7.5,\n \"complexity\": 8.5\n },\n \"description\": {\n \"en\": \"Barolo is a prestigious Italian red wine from Piedmont, made exclusively from Nebbiolo grapes. It is known for its pronounced tannins, high acidity, aromatic complexity with floral, fruit, and earthy notes, and excellent aging potential.\"\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "{} is not valid under any of the given schemas" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:barolo-docg", "expected": "ogs:core:beverage:barolo-docg", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "wine", "expected": "wine", "match": true } } }, "metrics": { "input_tokens": 2507, "output_tokens": 643, "latency_ms": 3816.0, "usd": 0.010158, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": -0.32, "ci95_hi": 0.9867, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2507.0, "output_tokens_mean": 612.333, "latency_ms_mean": 3708.433, "usd_sum": 0.029738 } }, { "task_id": "ogs:core:benchmark-task:struct-012", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "hard", "cuisine_region": "scottish", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "bd330891a3e68b59", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing 'Islay single malt' as an OGS beverage. It MUST validate against the OGS beverage schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"beverage_name\": \"Islay single malt\",\n \"namespace\": \"core\",\n \"id_slug\": \"ardbeg-10-islay\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:ardbeg-10-islay", "ogs_version": "0.1.0", "type": "spirit" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:ardbeg-10-islay\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Islay single malt\",\n \"type\": \"spirit\",\n \"subtype\": \"Scotch whisky\",\n \"region\": \"Islay, Scotland\",\n \"producer\": \"Ardbeg\",\n \"abv\": 46.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 1.5,\n \"salty\": 2,\n \"bitter\": 3,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 1,\n \"tannin\": 0.5,\n \"astringency\": 2,\n \"alcohol_heat\": 6.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"peat smoke\",\n \"item\": \"peat smoke\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea spray\",\n \"item\": \"seaweed\",\n \"intensity\": 4\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"charred oak\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"black pepper\",\n \"intensity\": 2\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon zest\",\n \"qualifier\": \"zest\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"malt\",\n \"item\": \"barley sugar\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"oily\",\n \"warming\"\n ],\n \"finish_length\": 8,\n \"complexity\": 7\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:ardbeg-10-islay", "expected": "ogs:core:beverage:ardbeg-10-islay", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "spirit", "expected": "spirit", "match": true } } }, "metrics": { "input_tokens": 2513, "output_tokens": 487, "latency_ms": 2853.9, "usd": 0.008922, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:ardbeg-10-islay\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Islay single malt\",\n \"type\": \"spirit\",\n \"subtype\": \"Scotch whisky\",\n \"region\": \"Islay\",\n \"producer\": \"Ardbeg\",\n \"abv\": 46.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 1.5,\n \"salty\": 2,\n \"bitter\": 3,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 1,\n \"tannin\": 0.5,\n \"astringency\": 2,\n \"alcohol_heat\": 6,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"smoke\",\n \"item\": \"peat\",\n \"intensity\": 8\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea\",\n \"item\": \"seaweed\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"charred wood\",\n \"intensity\": 4\n },\n {\n \"family\": \"spice\",\n \"group\": \"pepper\",\n \"item\": \"white pepper\",\n \"intensity\": 3\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon zest\",\n \"qualifier\": \"zest\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"smoked bacon\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"oily\",\n \"warming\"\n ],\n \"finish_length\": 7,\n \"complexity\": 7\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:ardbeg-10-islay", "expected": "ogs:core:beverage:ardbeg-10-islay", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "spirit", "expected": "spirit", "match": true } } }, "metrics": { "input_tokens": 2513, "output_tokens": 478, "latency_ms": 3460.7, "usd": 0.00885, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:ardbeg-10-islay\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": {\n \"en\": \"Islay single malt\"\n },\n \"type\": \"spirit\",\n \"subtype\": \"Scotch whisky\",\n \"region\": {\n \"en\": \"Islay, Scotland\"\n },\n \"producer\": {\n \"en\": \"Ardbeg\"\n },\n \"abv\": 46.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 1,\n \"salty\": 2,\n \"bitter\": 2.5,\n \"umami\": 2\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 1.5,\n \"tannin\": 0.5,\n \"astringency\": 1.5,\n \"alcohol_heat\": 6.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"peat\",\n \"item\": \"smoke\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea-air\",\n \"item\": \"seaweed\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"spice\",\n \"group\": \"oak-spice\",\n \"item\": \"black pepper\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"zest\",\n \"intensity\": 3\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"charred wood\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"medicinal\",\n \"item\": \"iodine\",\n \"intensity\": 5.5\n }\n ],\n \"texture\": [\n \"oily\",\n \"warming\"\n ],\n \"finish_length\": 8,\n \"complexity\": 7\n },\n \"description\": {\n \"en\": \"A classic Islay single malt whisky known for intense peat smoke, maritime and medicinal notes, supported by citrus and spice over a robust, oily body.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:ardbeg-10-islay", "expected": "ogs:core:beverage:ardbeg-10-islay", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "spirit", "expected": "spirit", "match": true } } }, "metrics": { "input_tokens": 2513, "output_tokens": 564, "latency_ms": 3269.8, "usd": 0.009538, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2513.0, "output_tokens_mean": 509.667, "latency_ms_mean": 3194.8, "usd_sum": 0.02731 } }, { "task_id": "ogs:core:benchmark-task:struct-013", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "872d23f39307a374", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing 'junmai ginjo sake' as an OGS beverage. It MUST validate against the OGS beverage schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"beverage_name\": \"junmai ginjo sake\",\n \"namespace\": \"core\",\n \"id_slug\": \"junmai-ginjo-generic\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:junmai-ginjo-generic", "ogs_version": "0.1.0", "type": "sake" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:junmai-ginjo-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"junmai ginjo sake\",\n \"type\": \"sake\",\n \"subtype\": \"junmai ginjo\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 3.5\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 2.5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 3.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tree fruit\",\n \"item\": \"pear\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n },\n {\n \"family\": \"fruit\",\n \"group\": \"melon\",\n \"item\": \"melon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flowers\",\n \"item\": \"lily\",\n \"intensity\": 1.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"rice\",\n \"item\": \"steamed rice\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"smooth\",\n \"silky\"\n ],\n \"finish_length\": 4,\n \"complexity\": 4\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:junmai-ginjo-generic", "expected": "ogs:core:beverage:junmai-ginjo-generic", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "sake", "expected": "sake", "match": true } } }, "metrics": { "input_tokens": 2516, "output_tokens": 389, "latency_ms": 2729.0, "usd": 0.008144, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:junmai-ginjo-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"junmai ginjo sake\",\n \"type\": \"sake\",\n \"subtype\": \"junmai ginjo\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 1.5,\n \"umami\": 5\n },\n \"structural\": {\n \"body\": 4,\n \"acidity_perception\": 2.5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 3,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"melon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"pear\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"lily\",\n \"intensity\": 3\n },\n {\n \"family\": \"confection\",\n \"group\": \"rice\",\n \"item\": \"steamed rice\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"silky\",\n \"smooth\"\n ],\n \"finish_length\": 6,\n \"complexity\": 5.5\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:junmai-ginjo-generic", "expected": "ogs:core:beverage:junmai-ginjo-generic", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "sake", "expected": "sake", "match": true } } }, "metrics": { "input_tokens": 2516, "output_tokens": 391, "latency_ms": 2927.9, "usd": 0.00816, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:junmai-ginjo-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"junmai ginjo sake\",\n \"type\": \"sake\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 2.5,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 5\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 3,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 2.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"peach\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"melon\",\n \"item\": \"honeydew\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"lily\",\n \"intensity\": 2\n },\n {\n \"family\": \"dairy\",\n \"group\": \"yogurt\",\n \"item\": \"yogurt\",\n \"intensity\": 1.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"rice\",\n \"item\": \"steamed rice\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\"silky\", \"light\"],\n \"finish_length\": 3.5,\n \"complexity\": 4\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:junmai-ginjo-generic", "expected": "ogs:core:beverage:junmai-ginjo-generic", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "sake", "expected": "sake", "match": true } } }, "metrics": { "input_tokens": 2516, "output_tokens": 413, "latency_ms": 2514.3, "usd": 0.008336, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2516.0, "output_tokens_mean": 397.667, "latency_ms_mean": 2723.733, "usd_sum": 0.02464 } }, { "task_id": "ogs:core:benchmark-task:struct-014", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "easy", "cuisine_region": "german", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "3fe3fe74f8d80260", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing 'Oktoberfest Märzen lager' as an OGS beverage. It MUST validate against the OGS beverage schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"beverage_name\": \"Oktoberfest Märzen lager\",\n \"namespace\": \"core\",\n \"id_slug\": \"oktoberfest-marzen\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:oktoberfest-marzen", "ogs_version": "0.1.0", "type": "beer" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"type\": \"beer\",\n \"subtype\": \"Märzen\",\n \"description\": \"A traditional German amber lager, rich and malty, brewed for Oktoberfest with toasty flavors and moderate bitterness.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 2.5,\n \"salty\": 0,\n \"bitter\": 3.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 5.5,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 3,\n \"effervescence\": 3.5\n },\n \"aromatics\": [\n {\n \"family\": \"malt\",\n \"group\": \"malt\",\n \"item\": \"toasted bread\",\n \"intensity\": 5\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramelized sugar\",\n \"item\": \"light caramel\",\n \"intensity\": 3\n },\n {\n \"family\": \"earth\",\n \"group\": \"grain\",\n \"item\": \"cereal\",\n \"intensity\": 2\n },\n {\n \"family\": \"herbal\",\n \"group\": \"hop-derived\",\n \"item\": \"noble hop\",\n \"intensity\": 2.5\n }\n ],\n \"texture\": [\n \"smooth\",\n \"medium-bodied\"\n ],\n \"finish_length\": 4,\n \"complexity\": 4.5\n },\n \"abv\": 5.8,\n \"serve_temperature_c\": {\n \"min\": 7,\n \"max\": 10\n },\n \"metadata\": {\n \"created\": \"2024-06-12T00:00:00Z\"\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'malt' is not one of ['fruit', 'floral', 'herbal', 'spice', 'earth', 'wood', 'dairy', 'savory', 'confection', 'vegetal', 'marine']" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:oktoberfest-marzen", "expected": "ogs:core:beverage:oktoberfest-marzen", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "beer", "expected": "beer", "match": true } } }, "metrics": { "input_tokens": 2516, "output_tokens": 466, "latency_ms": 2903.4, "usd": 0.00876, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"type\": \"beer\",\n \"subtype\": \"Märzen (Oktoberfest lager)\",\n \"description\": \"A traditional German amber lager brewed for Oktoberfest, noted for its clean malt-forward profile, moderate bitterness, and toasty character.\",\n \"abv\": 5.8,\n \"serve_temperature_c\": {\n \"min\": 7,\n \"max\": 10\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 1.5,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 4,\n \"acidity_perception\": 1.5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 2,\n \"effervescence\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"caramelized\",\n \"item\": \"caramel\",\n \"intensity\": 4\n },\n {\n \"family\": \"confection\",\n \"group\": \"toasted\",\n \"item\": \"toffee\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"cereal\",\n \"item\": \"bread crust\",\n \"intensity\": 3\n },\n {\n \"family\": \"herbal\",\n \"group\": \"hop\",\n \"item\": \"noble hop\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"smooth\",\n \"medium carbonation\"\n ],\n \"finish_length\": 3,\n \"complexity\": 4.5\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:oktoberfest-marzen", "expected": "ogs:core:beverage:oktoberfest-marzen", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "beer", "expected": "beer", "match": true } } }, "metrics": { "input_tokens": 2516, "output_tokens": 444, "latency_ms": 3003.5, "usd": 0.008584, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"type\": \"beer\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 1.5,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 1.5,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 2,\n \"effervescence\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"malt\",\n \"group\": \"grain\",\n \"item\": \"caramel\",\n \"intensity\": 6\n },\n {\n \"family\": \"malt\",\n \"group\": \"grain\",\n \"item\": \"bread crust\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"apricot\",\n \"intensity\": 2\n },\n {\n \"family\": \"spice\",\n \"group\": \"hop\",\n \"item\": \"herbal\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"smooth\",\n \"clean\",\n \"medium-bodied\"\n ],\n \"finish_length\": 4,\n \"complexity\": 3.5\n },\n \"description\": \"A traditional German amber lager style brewed for Oktoberfest, featuring rich toasty malt, smooth body, and a clean finish.\",\n \"abv\": 5.8,\n \"serve_temperature_c\": {\n \"min\": 7,\n \"max\": 10\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'malt' is not one of ['fruit', 'floral', 'herbal', 'spice', 'earth', 'wood', 'dairy', 'savory', 'confection', 'vegetal', 'marine']" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:oktoberfest-marzen", "expected": "ogs:core:beverage:oktoberfest-marzen", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "beer", "expected": "beer", "match": true } } }, "metrics": { "input_tokens": 2516, "output_tokens": 423, "latency_ms": 3275.3, "usd": 0.008416, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": -0.32, "ci95_hi": 0.9867, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2516.0, "output_tokens_mean": 444.333, "latency_ms_mean": 3060.733, "usd_sum": 0.02576 } }, { "task_id": "ogs:core:benchmark-task:struct-015", "category": "structured_output", "capability": "schema_valid_pairing", "difficulty": "hard", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.pairing", "vocab.match_types", "vocab.explanation_codes", "vocab.grade_scale", "id.format", "ogs_version" ], "prompt_template_hash": "f0c01fa20f35eb51", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS pairing schema (`schema/pairing.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/pairing.schema.json\",\n \"title\": \"OGS Pairing\",\n \"description\": \"A scored, explained pairing between a dish and a beverage.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"dish_ref\",\n \"beverage_ref\",\n \"match_types\",\n \"overall_score\",\n \"grade\",\n \"explanation_codes\",\n \"confidence\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:pairing:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"dish_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"beverage_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"match_types\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/match_type_entry\"\n }\n },\n \"overall_score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"grade\": {\n \"type\": \"string\",\n \"enum\": [\n \"A+\",\n \"A\",\n \"B+\",\n \"B\",\n \"C+\",\n \"C\",\n \"D\",\n \"F\"\n ]\n },\n \"explanation_codes\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/explanation_code_entry\"\n }\n },\n \"risks\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/risk_entry\"\n }\n },\n \"confidence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"evidence\": {\n \"$ref\": \"#/$defs/evidence\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"match_type_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"type\",\n \"score\"\n ],\n \"properties\": {\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"harmony\",\n \"contrast\",\n \"bridge\",\n \"intensity_alignment\",\n \"structural_balance\",\n \"refresh\"\n ]\n },\n \"score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"primary\": {\n \"type\": \"boolean\"\n }\n },\n \"additionalProperties\": false\n },\n \"explanation_code_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"weight\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"detail\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"risk_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\",\n \"severity\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"severity\": {\n \"type\": \"string\",\n \"enum\": [\n \"low\",\n \"medium\",\n \"high\"\n ]\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"mitigation\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"evidence\": {\n \"type\": \"object\",\n \"properties\": {\n \"method\": {\n \"type\": \"string\",\n \"enum\": [\n \"expert_panel\",\n \"instrumental\",\n \"computed\",\n \"estimated\"\n ]\n },\n \"sources\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n### OGS Explanation Codes\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS pairing JSON document for the described match. It MUST validate against the OGS pairing schema. Respond with ONLY the JSON.\n\nINPUT:\n{\n \"pairing_slug\": \"crottin-sancerre\",\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"intent\": \"Classic Loire regional pairing: Sancerre's acidity and citrus meet fresh goat cheese's tang.\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/pairing.schema.json", "required_fields": { "id": "ogs:core:pairing:crottin-sancerre", "ogs_version": "0.1.0", "dish_ref": "ogs:core:dish:crottin-de-chavignol", "beverage_ref": "ogs:core:beverage:sancerre-blanc" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Crottin de Chavignol & Sancerre Blanc\"\n },\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"match_types\": [\n {\n \"type\": \"harmony\",\n \"score\": 92,\n \"description\": {\n \"en\": \"Sancerre's citrus and mineral profile aligns seamlessly with the tangy, fresh character of young Crottin de Chavignol, creating a harmonious regional Loire match.\"\n },\n \"primary\": true\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 90,\n \"description\": {\n \"en\": \"The vibrant acidity of the Sancerre cleanses and balances the creamy texture and richness of the goat cheese.\"\n }\n },\n {\n \"type\": \"refresh\",\n \"score\": 88,\n \"description\": {\n \"en\": \"Sancerre's elevated acidity and mineral notes refresh the palate after each bite of cheese.\"\n }\n }\n ],\n \"overall_score\": 91,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.4,\n \"detail\": {\n \"en\": \"Both cheese and wine originate from the Loire Valley, amplifying regional synergy.\"\n }\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.3,\n \"detail\": {\n \"en\": \"The crisp acidity of Sancerre matches and balances the tang of the goat cheese.\"\n }\n },\n {\n \"code\": \"AROMA_SHARED_EARTH\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"Subtle earthy notes in both cheese and wine create additional aromatic bridge.\"\n }\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"High acidity in the wine cleanses the palate between bites.\"\n }\n }\n ],\n \"confidence\": 0.96,\n \"description\": {\n \"en\": \"Classic Loire Valley combination. The bright citrus and mineral drive of Sancerre harmonizes with the fresh tang of Crottin de Chavignol, both structurally and aromatically. Regional proximity intensifies the pairing’s sense of place.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:crottin-sancerre", "expected": "ogs:core:pairing:crottin-sancerre", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:crottin-de-chavignol", "expected": "ogs:core:dish:crottin-de-chavignol", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:sancerre-blanc", "expected": "ogs:core:beverage:sancerre-blanc", "match": true } } }, "metrics": { "input_tokens": 3382, "output_tokens": 578, "latency_ms": 6511.2, "usd": 0.011388, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Crottin de Chavignol & Sancerre Blanc Pairing\"\n },\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"match_types\": [\n {\n \"type\": \"harmony\",\n \"score\": 95,\n \"description\": {\n \"en\": \"The classic pairing from the Loire: Sancerre Blanc's zesty citrus and brisk acidity meet the tangy, creamy freshness of Crottin, creating a unified, harmonious taste.\"\n },\n \"primary\": true\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 90,\n \"description\": {\n \"en\": \"The wine's high acidity balances and complements the rich, tangy nature of the young goat cheese.\"\n }\n },\n {\n \"type\": \"refresh\",\n \"score\": 95,\n \"description\": {\n \"en\": \"Sancerre's piercing acidity refreshes the palate after each bite of Crottin de Chavignol.\"\n }\n }\n ],\n \"overall_score\": 97,\n \"grade\": \"A+\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.3,\n \"detail\": {\n \"en\": \"Both dish and wine originate from the Loire Valley, resulting in terroir-driven compatibility.\"\n }\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.3,\n \"detail\": {\n \"en\": \"The wine's high acidity balances the creamy tang and subtle fat of the goat cheese.\"\n }\n },\n {\n \"code\": \"AROMA_SHARED_EARTH\",\n \"weight\": 0.2,\n \"detail\": {\n \"en\": \"Both Crottin and Sancerre can exhibit mineral, earthy notes, providing additional aromatic synergy.\"\n }\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.2,\n \"detail\": {\n \"en\": \"Sancerre Blanc's acidity provides a palate-cleansing effect, enhancing enjoyment with each mouthful.\"\n }\n }\n ],\n \"confidence\": 0.99,\n \"description\": {\n \"en\": \"Classic regional pairing: The zesty citrus and mineral notes of Sancerre Blanc are a benchmark match for the creamy tang and subtle earthiness of Crottin de Chavignol goat cheese.\"\n },\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"sources\": [\n \"Kerin O’Keefe, 'Wine Pairing in France: Loire Valley', Decanter Magazine\",\n \"Jancis Robinson, 'Wine Grapes' (Sauvignon Blanc, Sancerre section)\",\n \"Le Guide Hachette des Vins 2022\"\n ],\n \"notes\": {\n \"en\": \"This pairing is highly traditional and frequently cited in authoritative wine and gastronomy references.\"\n }\n },\n \"metadata\": {\n \"created\": \"2024-06-01T12:00:00Z\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:crottin-sancerre", "expected": "ogs:core:pairing:crottin-sancerre", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:crottin-de-chavignol", "expected": "ogs:core:dish:crottin-de-chavignol", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:sancerre-blanc", "expected": "ogs:core:beverage:sancerre-blanc", "match": true } } }, "metrics": { "input_tokens": 3382, "output_tokens": 729, "latency_ms": 5315.3, "usd": 0.012596, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Crottin de Chavignol & Sancerre Blanc\"\n },\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"match_types\": [\n {\n \"type\": \"harmony\",\n \"score\": 92,\n \"description\": {\n \"en\": \"Both elements share an underlying tang (acidity/freshness) and are classic Loire Valley specialties.\"\n },\n \"primary\": true\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 90,\n \"description\": {\n \"en\": \"The vibrant acidity of Sancerre balances the richness and tang of the fresh goat cheese.\"\n }\n },\n {\n \"type\": \"bridge\",\n \"score\": 87,\n \"description\": {\n \"en\": \"Herbal and citrus notes in Sancerre echo subtle flavors in the Crottin de Chavignol.\"\n }\n },\n {\n \"type\": \"refresh\",\n \"score\": 88,\n \"description\": {\n \"en\": \"High acidity in the wine cleanses the palate, maintaining freshness with each bite.\"\n }\n }\n ],\n \"overall_score\": 92,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.3,\n \"detail\": {\n \"en\": \"Both cheese and wine originate from the Loire region, reinforcing their compatibility.\"\n }\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.3,\n \"detail\": {\n \"en\": \"Sancerre's lively acidity aligns with the cheese's tartness and cuts through its creaminess.\"\n }\n },\n {\n \"code\": \"AROMA_SHARED_HERBAL\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"Notes of fresh herbs in both wine and cheese create an aromatic bridge.\"\n }\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"The wine's acidity provides a bright, palate-cleansing effect.\"\n }\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.1,\n \"detail\": {\n \"en\": \"Goat cheese tang and Sauvignon Blanc citrus coalesce for a harmonious experience.\"\n }\n }\n ],\n \"confidence\": 0.95,\n \"description\": {\n \"en\": \"A benchmark Loire pairing: Sancerre's bright acidity and citrus notes perfectly match the fresh, tangy profile of Crottin de Chavignol, with regional affinity and palate-refreshing synergy.\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:crottin-sancerre", "expected": "ogs:core:pairing:crottin-sancerre", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:crottin-de-chavignol", "expected": "ogs:core:dish:crottin-de-chavignol", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:sancerre-blanc", "expected": "ogs:core:beverage:sancerre-blanc", "match": true } } }, "metrics": { "input_tokens": 3382, "output_tokens": 659, "latency_ms": 4576.2, "usd": 0.012036, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3382.0, "output_tokens_mean": 655.333, "latency_ms_mean": 5467.567, "usd_sum": 0.03602 } }, { "task_id": "ogs:core:benchmark-task:struct-016", "category": "structured_output", "capability": "schema_valid_dish", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "schema_validation", "context_needs": [ "schema.dish", "vocab.component_roles", "vocab.cooking_methods", "vocab.courses", "vocab.service_temperatures", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "284b25ae8f0dc3ef", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS dish schema (`schema/dish.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/dish.schema.json\",\n \"title\": \"OGS Dish\",\n \"description\": \"A composed dish with components, cooking methods, and overall sensory profile.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"components\",\n \"overall_sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"cuisine\": {\n \"type\": \"string\",\n \"description\": \"Free-text cuisine name (v0.1) OR a cuisine entity reference matching ogs::cuisine: (v0.2+).\"\n },\n \"course\": {\n \"type\": \"string\",\n \"enum\": [\n \"amuse\",\n \"appetizer\",\n \"soup\",\n \"salad\",\n \"fish\",\n \"main\",\n \"cheese\",\n \"dessert\",\n \"petit_four\"\n ]\n },\n \"service_temperature\": {\n \"type\": \"string\",\n \"enum\": [\n \"frozen\",\n \"cold\",\n \"cool\",\n \"room\",\n \"warm\",\n \"hot\",\n \"very_hot\"\n ]\n },\n \"components\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/component\"\n }\n },\n \"overall_sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"component\": {\n \"type\": \"object\",\n \"required\": [\n \"role\",\n \"ingredient_ref\"\n ],\n \"properties\": {\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"main_protein\",\n \"main_vegetable\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n ]\n },\n \"ingredient_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\"\n },\n \"cooking_method\": {\n \"type\": \"string\",\n \"enum\": [\n \"raw\",\n \"seared\",\n \"grilled\",\n \"roasted\",\n \"braised\",\n \"poached\",\n \"steamed\",\n \"fried\",\n \"confit\",\n \"smoked\",\n \"fermented\",\n \"cured\",\n \"pickled\",\n \"dehydrated\",\n \"sous_vide\",\n \"blanched\",\n \"sauteed\",\n \"baked\",\n \"charred\",\n \"emulsified\"\n ]\n },\n \"maillard_index\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"reduction_level\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"proportion\": {\n \"type\": \"string\",\n \"enum\": [\n \"dominant\",\n \"significant\",\n \"accent\",\n \"trace\"\n ]\n },\n \"sensory_contribution\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS dish JSON for tonkotsu ramen (pork-bone broth, wheat noodles, chashu, soft egg, nori, scallion). Respond with ONLY the JSON.\n\nINPUT:\n{\n \"dish_name\": \"tonkotsu ramen\",\n \"namespace\": \"core\",\n \"id_slug\": \"tonkotsu-ramen\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/dish.schema.json", "required_fields": { "id": "ogs:core:dish:tonkotsu-ramen", "ogs_version": "0.1.0", "course": "main" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:dish:tonkotsu-ramen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"tonkotsu ramen\",\n \"components\": [\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:tonkotsu-broth\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0.5,\n \"salty\": 6,\n \"bitter\": 0.5,\n \"umami\": 8\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"broth\",\n \"item\": \"pork bone\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"roots\",\n \"item\": \"garlic\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"rich\",\n \"unctuous\"\n ]\n }\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:wheat-ramen-noodle\",\n \"cooking_method\": \"boiled\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 1.5,\n \"bitter\": 0,\n \"umami\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"grain\",\n \"item\": \"wheat\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"springy\",\n \"slippery\"\n ]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:pork-chashu\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0,\n \"salty\": 4,\n \"bitter\": 0.5,\n \"umami\": 7\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meat\",\n \"item\": \"pork\",\n \"intensity\": 6\n },\n {\n \"family\": \"spice\",\n \"group\": \"aromatic\",\n \"item\": \"soy\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"tender\",\n \"fatty\"\n ]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:soft-boiled-egg\",\n \"cooking_method\": \"boiled\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 2.5,\n \"bitter\": 0,\n \"umami\": 4\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"egg\",\n \"item\": \"yolk\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"creamy\",\n \"soft\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 2,\n \"bitter\": 0.5,\n \"umami\": 3.5\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"papery\",\n \"delicate\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:scallion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0.5\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"crisp\"\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0.5,\n \"salty\": 6.5,\n \"bitter\": 0.5,\n \"umami\": 9\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"broth\",\n \"item\": \"pork bone\",\n \"intensity\": 8\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 3\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"rich\",\n \"unctuous\",\n \"springy\",\n \"tender\",\n \"creamy\",\n \"crisp\"\n ],\n \"finish_length\": 8,\n \"complexity\": 8.5\n },\n \"course\": \"main\",\n \"service_temperature\": \"hot\"\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'boiled' is not one of ['raw', 'seared', 'grilled', 'roasted', 'braised', 'poached', 'steamed', 'fried', 'confit', 'smoked', 'fermented', 'cured', 'pickled', 'dehydrated', 'sous_vide', 'blanched', 'sauteed', 'baked', 'charred', 'emulsified']" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:tonkotsu-ramen", "expected": "ogs:core:dish:tonkotsu-ramen", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "course": { "predicted": "main", "expected": "main", "match": true } } }, "metrics": { "input_tokens": 3078, "output_tokens": 1462, "latency_ms": 8000.6, "usd": 0.017852, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:dish:tonkotsu-ramen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"tonkotsu ramen\",\n \"components\": [\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:tonkotsu-broth\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0.5,\n \"salty\": 6,\n \"bitter\": 0.5,\n \"umami\": 8\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"broth\",\n \"item\": \"bone\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\n \"rich\",\n \"unctuous\",\n \"creamy\"\n ]\n }\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:wheat-ramen-noodle\",\n \"cooking_method\": \"boiled\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 1,\n \"bitter\": 0,\n \"umami\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"cereal\",\n \"item\": \"wheat\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"springy\",\n \"slippery\"\n ]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:chashu-pork\",\n \"cooking_method\": \"braised\",\n \"maillard_index\": 2,\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0,\n \"salty\": 3,\n \"bitter\": 0,\n \"umami\": 8\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork\",\n \"intensity\": 7\n },\n {\n \"family\": \"spice\",\n \"group\": \"braising\",\n \"item\": \"soy-sauce\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"tender\",\n \"succulent\"\n ]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:ramen-egg\",\n \"cooking_method\": \"boiled\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 1,\n \"bitter\": 0,\n \"umami\": 3.5\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"eggy\",\n \"item\": \"egg\",\n \"intensity\": 3.5\n }\n ],\n \"texture\": [\n \"creamy\",\n \"soft\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 2.5,\n \"bitter\": 0,\n \"umami\": 4\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"papery\",\n \"crisp\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:scallion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"trace\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"crisp\",\n \"fresh\"\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0.2,\n \"salty\": 6,\n \"bitter\": 0.2,\n \"umami\": 8.5\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 0.2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"broth\",\n \"item\": \"bone\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"rich\",\n \"unctuous\",\n \"springy\",\n \"tender\",\n \"creamy\",\n \"crisp\"\n ],\n \"finish_length\": 8,\n \"complexity\": 8\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'boiled' is not one of ['raw', 'seared', 'grilled', 'roasted', 'braised', 'poached', 'steamed', 'fried', 'confit', 'smoked', 'fermented', 'cured', 'pickled', 'dehydrated', 'sous_vide', 'blanched', 'sauteed', 'baked', 'charred', 'emulsified']" ], "consistent": false, "required_fields": { "id": { "predicted": "ogs:core:dish:tonkotsu-ramen", "expected": "ogs:core:dish:tonkotsu-ramen", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "course": { "predicted": null, "expected": "main", "match": false } } }, "metrics": { "input_tokens": 3078, "output_tokens": 1498, "latency_ms": 7753.1, "usd": 0.01814, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:dish:tonkotsu-ramen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"tonkotsu ramen\",\n \"components\": [\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:pork-bone-broth\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 5.5,\n \"bitter\": 0,\n \"umami\": 8.5\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork_bone\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"minerality\",\n \"item\": \"bone_broth\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"rich\",\n \"unctuous\",\n \"brothy\"\n ]\n }\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:wheat-noodle\",\n \"cooking_method\": \"boiled\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0,\n \"salty\": 1,\n \"bitter\": 0,\n \"umami\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"cereal\",\n \"item\": \"wheat\",\n \"intensity\": 3.5\n }\n ],\n \"texture\": [\n \"springy\",\n \"slippery\"\n ]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:chashu\",\n \"cooking_method\": \"braised\",\n \"maillard_index\": 2,\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0,\n \"salty\": 5,\n \"bitter\": 0,\n \"umami\": 6.5\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork\",\n \"intensity\": 7\n },\n {\n \"family\": \"spice\",\n \"group\": \"soy_sauce\",\n \"item\": \"soy_sauce\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"tender\",\n \"succulent\",\n \"fatty\"\n ]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:soft-boiled-egg\",\n \"cooking_method\": \"boiled\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 1.5,\n \"bitter\": 0,\n \"umami\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"eggy\",\n \"item\": \"egg\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"silky\",\n \"creamy\",\n \"tender\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 2,\n \"bitter\": 0.5,\n \"umami\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"crisp\",\n \"delicate\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:scallion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 0.5\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"crisp\",\n \"juicy\"\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0,\n \"salty\": 6,\n \"bitter\": 0.3,\n \"umami\": 9\n },\n \"structural\": {\n \"body\": 8.5,\n \"acidity_perception\": 0,\n \"tannin\": 0,\n \"astringency\": 0.3,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork_bone\",\n \"intensity\": 8\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 4\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"unctuous\",\n \"brothy\",\n \"springy\",\n \"succulent\",\n \"silky\"\n ],\n \"finish_length\": 7,\n \"complexity\": 8\n },\n \"course\": \"main\",\n \"service_temperature\": \"hot\"\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'boiled' is not one of ['raw', 'seared', 'grilled', 'roasted', 'braised', 'poached', 'steamed', 'fried', 'confit', 'smoked', 'fermented', 'cured', 'pickled', 'dehydrated', 'sous_vide', 'blanched', 'sauteed', 'baked', 'charred', 'emulsified']" ], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:tonkotsu-ramen", "expected": "ogs:core:dish:tonkotsu-ramen", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "course": { "predicted": "main", "expected": "main", "match": true } } }, "metrics": { "input_tokens": 3078, "output_tokens": 1504, "latency_ms": 7813.5, "usd": 0.018188, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3078.0, "output_tokens_mean": 1488.0, "latency_ms_mean": 7855.733, "usd_sum": 0.05418 } }, { "task_id": "ogs:core:benchmark-task:struct-017", "category": "structured_output", "capability": "schema_valid_dish", "difficulty": "medium", "cuisine_region": "mexican", "scorer": "schema_validation", "context_needs": [ "schema.dish", "vocab.component_roles", "vocab.cooking_methods", "vocab.courses", "vocab.service_temperatures", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "534d8590759d6dc3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS dish schema (`schema/dish.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/dish.schema.json\",\n \"title\": \"OGS Dish\",\n \"description\": \"A composed dish with components, cooking methods, and overall sensory profile.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"components\",\n \"overall_sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"cuisine\": {\n \"type\": \"string\",\n \"description\": \"Free-text cuisine name (v0.1) OR a cuisine entity reference matching ogs::cuisine: (v0.2+).\"\n },\n \"course\": {\n \"type\": \"string\",\n \"enum\": [\n \"amuse\",\n \"appetizer\",\n \"soup\",\n \"salad\",\n \"fish\",\n \"main\",\n \"cheese\",\n \"dessert\",\n \"petit_four\"\n ]\n },\n \"service_temperature\": {\n \"type\": \"string\",\n \"enum\": [\n \"frozen\",\n \"cold\",\n \"cool\",\n \"room\",\n \"warm\",\n \"hot\",\n \"very_hot\"\n ]\n },\n \"components\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/component\"\n }\n },\n \"overall_sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"component\": {\n \"type\": \"object\",\n \"required\": [\n \"role\",\n \"ingredient_ref\"\n ],\n \"properties\": {\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"main_protein\",\n \"main_vegetable\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n ]\n },\n \"ingredient_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\"\n },\n \"cooking_method\": {\n \"type\": \"string\",\n \"enum\": [\n \"raw\",\n \"seared\",\n \"grilled\",\n \"roasted\",\n \"braised\",\n \"poached\",\n \"steamed\",\n \"fried\",\n \"confit\",\n \"smoked\",\n \"fermented\",\n \"cured\",\n \"pickled\",\n \"dehydrated\",\n \"sous_vide\",\n \"blanched\",\n \"sauteed\",\n \"baked\",\n \"charred\",\n \"emulsified\"\n ]\n },\n \"maillard_index\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"reduction_level\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"proportion\": {\n \"type\": \"string\",\n \"enum\": [\n \"dominant\",\n \"significant\",\n \"accent\",\n \"trace\"\n ]\n },\n \"sensory_contribution\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS dish JSON for pico de gallo (tomato, onion, cilantro, jalapeño, lime). JSON only.\n\nINPUT:\n{\n \"dish_name\": \"pico de gallo\",\n \"namespace\": \"core\",\n \"id_slug\": \"pico-de-gallo\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/dish.schema.json", "required_fields": { "id": "ogs:core:dish:pico-de-gallo", "ogs_version": "0.1.0" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:dish:pico-de-gallo\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"pico de gallo\",\n \"components\": [\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:tomato\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"nightshade\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\"juicy\", \"crisp\"]\n }\n },\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:onion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\"crisp\", \"sharp\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:cilantro\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"green_herbs\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\"leafy\"]\n }\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:jalapeno\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"capsicum\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\"crisp\", \"pungent\"]\n }\n },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:lime\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 7,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\"juicy\"]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 4.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 1.5,\n \"acidity_perception\": 5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"nightshade\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green_herbs\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"capsicum\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\"juicy\", \"crisp\", \"leafy\", \"pungent\"],\n \"finish_length\": 3,\n \"complexity\": 5\n },\n \"course\": \"appetizer\",\n \"service_temperature\": \"cool\"\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:pico-de-gallo", "expected": "ogs:core:dish:pico-de-gallo", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 3063, "output_tokens": 1295, "latency_ms": 6452.3, "usd": 0.016486, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:dish:pico-de-gallo\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"pico de gallo\",\n \"components\": [\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:tomato\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"berry\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\"juicy\", \"crunchy\"]\n }\n },\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:onion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\"crisp\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:cilantro\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\"leafy\"]\n }\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:jalapeno\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"chili\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\"crisp\"]\n }\n },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:lime\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 6,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n }\n ],\n \"texture\": []\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 3.5,\n \"salty\": 0.5,\n \"bitter\": 0.5,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 7,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"berry\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"chili\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\"juicy\", \"crisp\", \"chunky\"],\n \"finish_length\": 3,\n \"complexity\": 4\n },\n \"course\": \"appetizer\",\n \"service_temperature\": \"cool\"\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:pico-de-gallo", "expected": "ogs:core:dish:pico-de-gallo", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 3063, "output_tokens": 1280, "latency_ms": 7255.5, "usd": 0.016366, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:dish:pico-de-gallo\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"pico de gallo\",\n \"components\": [\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:tomato\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"fleshy\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\"juicy\", \"firm\", \"crunchy\"]\n }\n },\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:onion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\"crunchy\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:cilantro\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\"leafy\", \"fresh\"]\n }\n },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:lime\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\"juicy\"]\n }\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:jalapeno\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"pepper\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\"crunchy\"]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 4.5,\n \"salty\": 0.5,\n \"bitter\": 0.5,\n \"umami\": 0.5\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"fleshy\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n },\n {\n \"family\": \"savory\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"pepper\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3.5\n }\n ],\n \"texture\": [\"crunchy\", \"juicy\", \"fresh\"],\n \"finish_length\": 3,\n \"complexity\": 6\n },\n \"course\": \"appetizer\",\n \"service_temperature\": \"cool\"\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:pico-de-gallo", "expected": "ogs:core:dish:pico-de-gallo", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 3063, "output_tokens": 1305, "latency_ms": 7117.7, "usd": 0.016566, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3063.0, "output_tokens_mean": 1293.333, "latency_ms_mean": 6941.833, "usd_sum": 0.049418 } }, { "task_id": "ogs:core:benchmark-task:struct-018", "category": "structured_output", "capability": "sensory_profile_json", "difficulty": "medium", "cuisine_region": "french", "scorer": "json_match", "context_needs": [ "scales.basic_tastes", "scales.structural", "vocab.aromatic_families", "vocab.qualifiers" ], "prompt_template_hash": "1470a28b8e9ef028", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nProduce a JSON sensory profile for 24-month aged Comté cheese. Keys: basic_tastes, structural, aromatics. All intensities on 0-10. JSON only.\n\nINPUT:\n{\n \"item\": \"24-month aged Comté\"\n}\n\nANSWER FORMAT: json", "expected": { "value": { "basic_tastes": { "sweet": 2.0, "sour": 2.0, "salty": 5.0, "bitter": 1.5, "umami": 8.0 }, "structural": { "body": 7.0, "acidity_perception": 3.0, "tannin": 0, "astringency": 0, "alcohol_heat": 0, "effervescence": 0 } }, "required_keys": [ "basic_tastes.umami", "basic_tastes.salty", "structural.body" ] }, "samples": [ { "sample": 0, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 1.5,\n \"salty\": 4.5,\n \"bitter\": 1.0,\n \"umami\": 7.0\n },\n \"structural\": {\n \"body\": 8.0,\n \"acidity_perception\": 2.0,\n \"tannin\": 0.0,\n \"astringency\": 1.0,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\"family\": \"dairy\", \"qualifier\": \"cooked\", \"intensity\": 8.0},\n {\"family\": \"nut\", \"qualifier\": \"roasted\", \"intensity\": 7.0},\n {\"family\": \"earth\", \"qualifier\": \"fermented\", \"intensity\": 5.0},\n {\"family\": \"fruit\", \"qualifier\": \"dried\", \"intensity\": 3.0},\n {\"family\": \"spice\", \"qualifier\": \"cooked\", \"intensity\": 2.0}\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 7.0, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 4.5, "expected": 5.0, "match": true }, "structural.body": { "predicted": 8.0, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 454, "output_tokens": 263, "latency_ms": 2044.6, "usd": 0.003012, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 2.0,\n \"salty\": 4.5,\n \"bitter\": 1.5,\n \"umami\": 7.5\n },\n \"structural\": {\n \"body\": 8.0,\n \"acidity_perception\": 2.5,\n \"tannin\": 0.5,\n \"astringency\": 1.0,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\"family\": \"dairy\", \"qualifier\": \"cooked\"},\n {\"family\": \"nut\", \"qualifier\": \"roasted\"},\n {\"family\": \"savory\"},\n {\"family\": \"earth\"},\n {\"family\": \"spice\", \"qualifier\": \"dried\"},\n {\"family\": \"wood\"},\n {\"family\": \"fruit\", \"qualifier\": \"dried\"}\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 7.5, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 4.5, "expected": 5.0, "match": true }, "structural.body": { "predicted": 8.0, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 454, "output_tokens": 225, "latency_ms": 1627.0, "usd": 0.002708, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 1,\n \"salty\": 4,\n \"bitter\": 1.5,\n \"umami\": 7\n },\n \"structural\": {\n \"body\": 7.5,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"qualifier\": \"cooked\",\n \"intensity\": 8\n },\n {\n \"family\": \"nut\",\n \"qualifier\": \"roasted\",\n \"intensity\": 7\n },\n {\n \"family\": \"earth\",\n \"qualifier\": \"fresh\",\n \"intensity\": 2\n },\n {\n \"family\": \"savory\",\n \"qualifier\": \"fermented\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"qualifier\": \"dried\",\n \"intensity\": 3\n }\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 7, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 4, "expected": 5.0, "match": true }, "structural.body": { "predicted": 7.5, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 454, "output_tokens": 266, "latency_ms": 1731.1, "usd": 0.003036, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 454.0, "output_tokens_mean": 251.333, "latency_ms_mean": 1800.9, "usd_sum": 0.008756 } }, { "task_id": "ogs:core:benchmark-task:struct-019", "category": "structured_output", "capability": "sensory_profile_json", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "json_match", "context_needs": [ "scales.basic_tastes", "scales.structural", "vocab.aromatic_families", "vocab.qualifiers" ], "prompt_template_hash": "aa2726470aa7cfb8", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nProduce a JSON sensory profile for blistered shishito peppers lightly salted. Keys: basic_tastes, structural, aromatics.\n\nINPUT:\n{\n \"item\": \"blistered shishito peppers with flaky salt\"\n}\n\nANSWER FORMAT: json", "expected": { "value": { "basic_tastes": { "sweet": 2.0, "sour": 1.0, "salty": 5.0, "bitter": 3.0, "umami": 2.0 }, "structural": { "body": 3.0, "acidity_perception": 2.0, "tannin": 0, "astringency": 1.0, "alcohol_heat": 0, "effervescence": 0 } }, "required_keys": [ "basic_tastes.salty", "basic_tastes.bitter", "structural.body" ] }, "samples": [ { "sample": 0, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 1,\n \"salty\": 3,\n \"bitter\": 1.5,\n \"umami\": 2\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 1,\n \"tannin\": 0.5,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"qualifiers\": [\"cooked\", \"fresh\"]\n },\n {\n \"family\": \"spice\",\n \"qualifiers\": [\"fresh\"]\n },\n {\n \"family\": \"earth\",\n \"qualifiers\": [\"cooked\"]\n }\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 3, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 1.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 2, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 448, "output_tokens": 191, "latency_ms": 1479.7, "usd": 0.002424, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 3,\n \"bitter\": 2,\n \"umami\": 2\n },\n \"structural\": {\n \"body\": 3.5,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"qualifiers\": [\"cooked\", \"fresh\"]\n },\n {\n \"family\": \"earth\",\n \"qualifiers\": [\"fresh\"]\n },\n {\n \"family\": \"spice\",\n \"qualifiers\": [\"fresh\"]\n }\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 3, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 2, "expected": 3.0, "match": true }, "structural.body": { "predicted": 3.5, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 448, "output_tokens": 186, "latency_ms": 1557.8, "usd": 0.002384, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0.5,\n \"salty\": 3.5,\n \"bitter\": 2.5,\n \"umami\": 4\n },\n \"structural\": {\n \"body\": 2.5,\n \"acidity_perception\": 0.5,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"qualifier\": \"cooked\"\n },\n {\n \"family\": \"spice\"\n },\n {\n \"family\": \"earth\",\n \"qualifier\": \"fresh\"\n }\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 3.5, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 2.5, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 448, "output_tokens": 183, "latency_ms": 1663.4, "usd": 0.00236, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 448.0, "output_tokens_mean": 186.667, "latency_ms_mean": 1566.967, "usd_sum": 0.007168 } }, { "task_id": "ogs:core:benchmark-task:struct-020", "category": "structured_output", "capability": "schema_valid_pairing", "difficulty": "expert", "cuisine_region": "mexican", "scorer": "schema_validation", "context_needs": [ "schema.pairing", "vocab.match_types", "vocab.explanation_codes", "vocab.grade_scale", "id.format", "ogs_version" ], "prompt_template_hash": "5b115600e8dad71f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS pairing schema (`schema/pairing.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/pairing.schema.json\",\n \"title\": \"OGS Pairing\",\n \"description\": \"A scored, explained pairing between a dish and a beverage.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"dish_ref\",\n \"beverage_ref\",\n \"match_types\",\n \"overall_score\",\n \"grade\",\n \"explanation_codes\",\n \"confidence\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:pairing:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"dish_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"beverage_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"match_types\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/match_type_entry\"\n }\n },\n \"overall_score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"grade\": {\n \"type\": \"string\",\n \"enum\": [\n \"A+\",\n \"A\",\n \"B+\",\n \"B\",\n \"C+\",\n \"C\",\n \"D\",\n \"F\"\n ]\n },\n \"explanation_codes\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/explanation_code_entry\"\n }\n },\n \"risks\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/risk_entry\"\n }\n },\n \"confidence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"evidence\": {\n \"$ref\": \"#/$defs/evidence\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"match_type_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"type\",\n \"score\"\n ],\n \"properties\": {\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"harmony\",\n \"contrast\",\n \"bridge\",\n \"intensity_alignment\",\n \"structural_balance\",\n \"refresh\"\n ]\n },\n \"score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"primary\": {\n \"type\": \"boolean\"\n }\n },\n \"additionalProperties\": false\n },\n \"explanation_code_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"weight\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"detail\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"risk_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\",\n \"severity\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"severity\": {\n \"type\": \"string\",\n \"enum\": [\n \"low\",\n \"medium\",\n \"high\"\n ]\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"mitigation\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"evidence\": {\n \"type\": \"object\",\n \"properties\": {\n \"method\": {\n \"type\": \"string\",\n \"enum\": [\n \"expert_panel\",\n \"instrumental\",\n \"computed\",\n \"estimated\"\n ]\n },\n \"sources\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n### OGS Explanation Codes\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS pairing JSON for mole-negro enchiladas with Aragonese Garnacha. JSON only.\n\nINPUT:\n{\n \"pairing_slug\": \"mole-negro-garnacha\",\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"intent\": \"Cross-cultural bridge pairing: ripe fruit and body handle chocolate-chile sauce.\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/pairing.schema.json", "required_fields": { "id": "ogs:core:pairing:mole-negro-garnacha", "ogs_version": "0.1.0", "dish_ref": "ogs:core:dish:mole-negro-enchiladas", "beverage_ref": "ogs:core:beverage:garnacha-aragon" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:pairing:mole-negro-garnacha\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Mole Negro Enchiladas & Aragonese Garnacha\"\n },\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"bridge\",\n \"score\": 85,\n \"description\": {\n \"en\": \"The ripe red fruit of Aragonese Garnacha echoes the dried fruits and cinnamon notes found in mole negro, creating an aromatic bridge.\"\n },\n \"primary\": true\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 80,\n \"description\": {\n \"en\": \"The body and moderate tannin of Garnacha stand up to the rich, velvety, chocolate-chile sauce.\"\n }\n },\n {\n \"type\": \"harmony\",\n \"score\": 80,\n \"description\": {\n \"en\": \"The earthy and smoky elements in both the enchiladas and Garnacha's terroir-driven character contribute to the pairing's unity.\"\n }\n }\n ],\n \"overall_score\": 87,\n \"grade\": \"B+\",\n \"explanation_codes\": [\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.3,\n \"detail\": {\n \"en\": \"Both elements feature spice: cinnamon, clove, and subtle pepper notes.\"\n }\n },\n {\n \"code\": \"AROMA_SHARED_EARTH\",\n \"weight\": 0.2,\n \"detail\": {\n \"en\": \"Earthy and smoky undertones appear in both the mole and Garnacha.\"\n }\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.2,\n \"detail\": {\n \"en\": \"The weight of the wine matches the richness of the sauce.\"\n }\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.2,\n \"detail\": {\n \"en\": \"The Garnacha's intensity matches the bold flavors of the mole.\"\n }\n },\n {\n \"code\": \"STRUCT_TANNIN_FAT\",\n \"weight\": 0.1,\n \"detail\": {\n \"en\": \"Gentle tannins are softened by the dish's fat content.\"\n }\n }\n ],\n \"confidence\": 0.85,\n \"description\": {\n \"en\": \"A cross-cultural pairing that bridges Mexican mole negro enchiladas with Spanish Garnacha from Aragón. Ripe fruit, spice, and supple texture in the wine link to the dish's layers of chocolate, dried chiles, and spices, while balanced structure ensures neither element overwhelms.\"\n },\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"notes\": {\n \"en\": \"Based on culinary and sommelier panel consensus regarding the classic affinity between rich, sauced Mexican dishes and juicy, spice-accented Mediterranean reds.\"\n }\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:mole-negro-garnacha", "expected": "ogs:core:pairing:mole-negro-garnacha", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:mole-negro-enchiladas", "expected": "ogs:core:dish:mole-negro-enchiladas", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:garnacha-aragon", "expected": "ogs:core:beverage:garnacha-aragon", "match": true } } }, "metrics": { "input_tokens": 3372, "output_tokens": 688, "latency_ms": 5943.2, "usd": 0.012248, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:pairing:mole-negro-garnacha\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Mole Negro Enchiladas with Aragonese Garnacha\"\n },\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"bridge\",\n \"score\": 88,\n \"description\": {\n \"en\": \"Bridging through shared ripe fruit notes, mild spice and plush body; Garnacha connects with the chocolate, spice, and richness of mole negro.\",\n \"es\": \"Puente gracias a notas frutales maduras compartidas, especia suave y cuerpo generoso; la Garnacha enlaza con el chocolate, especias y riqueza del mole negro.\"\n },\n \"primary\": true\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 85,\n \"description\": {\n \"en\": \"The medium-full intensity and richness of the dish align well with the juicy, medium-bodied structure of Aragonese Garnacha.\"\n }\n },\n {\n \"type\": \"harmony\",\n \"score\": 80,\n \"description\": {\n \"en\": \"Roasted notes and gentle tannin harmonize with the earthy and chocolate flavors of mole.\"\n }\n }\n ],\n \"overall_score\": 87,\n \"grade\": \"B+\",\n \"explanation_codes\": [\n {\n \"code\": \"AROMA_SHARED_FRUIT\",\n \"weight\": 0.35,\n \"detail\": {\n \"en\": \"Both mole and Garnacha have pronounced, ripe fruit character (dried berries, raisin), forming an aromatic bridge.\"\n }\n },\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"Spice notes in both the chile-driven mole and the Garnacha (pepper, cinnamon) build aromatic cohesion.\"\n }\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.2,\n \"detail\": {\n \"en\": \"Mole's deep flavor and richness find balance in Garnacha’s generous fruit and structure.\"\n }\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"Medium-full body in both elements; the wine neither overwhelms nor is overpowered by the dish.\"\n }\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"Earthy, chocolate, and berry notes are echoed and integrated between dish and beverage.\"\n }\n }\n ],\n \"confidence\": 0.9,\n \"description\": {\n \"en\": \"Cross-cultural bridge pairing: ripe fruit and body handle chocolate-chile sauce. Garnacha’s fruit, supple body, and spicy warmth complement the earthy, chocolate, and spicy complexity of mole negro, allowing both to shine.\"\n },\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"sources\": [\n \"OGS Sommelier Panel, May 2024\",\n \"Comparative tasting: mole negro with New World Grenache\"\n ],\n \"notes\": {\n \"en\": \"Panelists noted successful matches with Grenache-based reds, and Aragonese Garnacha provided the optimal blend of fruit generosity, spice, and supple structure for mole negro.\"\n }\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:mole-negro-garnacha", "expected": "ogs:core:pairing:mole-negro-garnacha", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:mole-negro-enchiladas", "expected": "ogs:core:dish:mole-negro-enchiladas", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:garnacha-aragon", "expected": "ogs:core:beverage:garnacha-aragon", "match": true } } }, "metrics": { "input_tokens": 3372, "output_tokens": 788, "latency_ms": 6248.2, "usd": 0.013048, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:pairing:mole-negro-garnacha\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Mole Negro Enchiladas with Aragonese Garnacha\"\n },\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"bridge\",\n \"score\": 85,\n \"description\": {\n \"en\": \"Shared fruit and subtle spice notes create continuity between mole negro and Garnacha.\"\n },\n \"primary\": true\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 83,\n \"description\": {\n \"en\": \"Garnacha's body and supple tannins support the richness and chocolate-chile depth of mole negro.\"\n }\n },\n {\n \"type\": \"harmony\",\n \"score\": 81,\n \"description\": {\n \"en\": \"The wine's ripe dark fruit melds with the sauce's chocolate and fruit elements for a harmonious pairing.\"\n }\n }\n ],\n \"overall_score\": 83,\n \"grade\": \"B\",\n \"explanation_codes\": [\n {\n \"code\": \"AROMA_SHARED_FRUIT\",\n \"weight\": 0.35,\n \"detail\": {\n \"en\": \"Both the enchiladas' sauce and the wine show deep fruit notes that bridge their flavors.\"\n }\n },\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"Spice in the mole echoes subtle pepper notes in the Garnacha.\"\n }\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.25,\n \"detail\": {\n \"en\": \"The richness and intensity of both components are well matched.\"\n }\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"Garnacha's medium-full body keeps pace with the substantial sauce.\"\n }\n },\n {\n \"code\": \"STRUCT_TANNIN_FAT\",\n \"weight\": 0.1,\n \"detail\": {\n \"en\": \"Supple tannins in the wine are rounded by the fat content of the mole sauce.\"\n }\n }\n ],\n \"confidence\": 0.85,\n \"description\": {\n \"en\": \"A cross-cultural pairing where Aragonese Garnacha’s bold fruit, body, and spice harmonize and bridge with the chocolate, chile, and richness of mole negro enchiladas.\"\n },\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"sources\": [\n \"Traditional Mexican culinary texts\",\n \"Aragonese Garnacha producer tasting notes\"\n ]\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:mole-negro-garnacha", "expected": "ogs:core:pairing:mole-negro-garnacha", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:mole-negro-enchiladas", "expected": "ogs:core:dish:mole-negro-enchiladas", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:garnacha-aragon", "expected": "ogs:core:beverage:garnacha-aragon", "match": true } } }, "metrics": { "input_tokens": 3372, "output_tokens": 638, "latency_ms": 9570.7, "usd": 0.011848, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3372.0, "output_tokens_mean": 704.667, "latency_ms_mean": 7254.033, "usd_sum": 0.037144 } }, { "task_id": "ogs:core:benchmark-task:vocab-001", "category": "vocabulary", "capability": "aromatic_family_classification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "e52270d817a9dc7f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nUsing the OGS sensory model, return the single aromatic family (from the controlled vocabulary) that best classifies the aromatic item below. Respond with just the family name.\n\nINPUT:\n{\n \"item\": \"lemon zest\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "fruit" }, "samples": [ { "sample": 0, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 1, "latency_ms": 601.8, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 1, "latency_ms": 645.6, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 1, "latency_ms": 613.0, "usd": 0.000674, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 333.0, "output_tokens_mean": 1.0, "latency_ms_mean": 620.133, "usd_sum": 0.002022 } }, { "task_id": "ogs:core:benchmark-task:vocab-002", "category": "vocabulary", "capability": "aromatic_family_classification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "e2096242953ff882", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nUsing the OGS sensory model, return the single aromatic family that best classifies the item below. Respond with just the family name.\n\nINPUT:\n{\n \"item\": \"wet stone\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "earth" }, "samples": [ { "sample": 0, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 325, "output_tokens": 1, "latency_ms": 625.8, "usd": 0.000658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 325, "output_tokens": 1, "latency_ms": 622.1, "usd": 0.000658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 325, "output_tokens": 1, "latency_ms": 669.0, "usd": 0.000658, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 325.0, "output_tokens_mean": 1.0, "latency_ms_mean": 638.967, "usd_sum": 0.001974 } }, { "task_id": "ogs:core:benchmark-task:vocab-003", "category": "vocabulary", "capability": "aromatic_family_classification", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "fa5fa32bfe275dfb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nUsing the OGS sensory model, return the single aromatic family that best classifies the item below. Respond with just the family name.\n\nINPUT:\n{\n \"item\": \"cooked beef fat\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "savory" }, "samples": [ { "sample": 0, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 327, "output_tokens": 2, "latency_ms": 604.5, "usd": 0.00067, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 327, "output_tokens": 2, "latency_ms": 740.8, "usd": 0.00067, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 327, "output_tokens": 2, "latency_ms": 894.3, "usd": 0.00067, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 327.0, "output_tokens_mean": 2.0, "latency_ms_mean": 746.533, "usd_sum": 0.00201 } }, { "task_id": "ogs:core:benchmark-task:vocab-004", "category": "vocabulary", "capability": "cooking_method_vocabulary", "difficulty": "easy", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "e0631034b8b8ece4", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nPick the single OGS cooking method that best describes a protein slowly cooked while fully submerged in fat at a low temperature. Respond with just the method name from the OGS vocabulary.\n\nINPUT:\n{\n \"description\": \"duck legs slow-cooked submerged in their own rendered fat at 80 C\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "confit" }, "samples": [ { "sample": 0, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 407, "output_tokens": 2, "latency_ms": 627.1, "usd": 0.00083, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 407, "output_tokens": 2, "latency_ms": 681.9, "usd": 0.00083, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 407, "output_tokens": 2, "latency_ms": 1344.9, "usd": 0.00083, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 407.0, "output_tokens_mean": 2.0, "latency_ms_mean": 884.633, "usd_sum": 0.00249 } }, { "task_id": "ogs:core:benchmark-task:vocab-005", "category": "vocabulary", "capability": "match_type_vocabulary", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "bbbd81bb3c8b8ea4", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nSelect the single OGS match type that best describes a pairing whose strength is driven by a specific shared aromatic compound or family between dish and beverage.\n\nINPUT:\n{\n \"description\": \"dish and wine are linked by a shared earthy, forest-floor aromatic\"\n}\n\nANSWER FORMAT: one_of:harmony,contrast,bridge,intensity_alignment,structural_balance,refresh", "expected": { "value": "bridge" }, "samples": [ { "sample": 0, "raw_response": "harmony", "compliant": true, "score": 0.0, "detail": { "predicted": "harmony", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 317, "output_tokens": 2, "latency_ms": 591.6, "usd": 0.00065, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "harmony", "compliant": true, "score": 0.0, "detail": { "predicted": "harmony", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 317, "output_tokens": 2, "latency_ms": 624.1, "usd": 0.00065, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "bridge", "compliant": true, "score": 1.0, "detail": { "predicted": "bridge", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 317, "output_tokens": 1, "latency_ms": 650.4, "usd": 0.000642, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": -0.32, "ci95_hi": 0.9867, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 317.0, "output_tokens_mean": 1.667, "latency_ms_mean": 622.033, "usd_sum": 0.001942 } }, { "task_id": "ogs:core:benchmark-task:vocab-006", "category": "vocabulary", "capability": "component_role_vocabulary", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "6c6ae6f82f354be3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nReturn the single OGS component role that best fits the described element. Use only roles from the OGS controlled vocabulary.\n\nINPUT:\n{\n \"element\": \"a soy-dashi based liquid ladled over the rice bowl, providing salt, umami and moisture\"\n}\n\nANSWER FORMAT: one_of:main_protein,main_vegetable,starch,sauce,fat_component,acid_component,aromatic_garnish,seasoning,textural_element", "expected": { "value": "sauce" }, "samples": [ { "sample": 0, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 351, "output_tokens": 2, "latency_ms": 586.9, "usd": 0.000718, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 351, "output_tokens": 2, "latency_ms": 663.6, "usd": 0.000718, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 351, "output_tokens": 2, "latency_ms": 586.0, "usd": 0.000718, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 351.0, "output_tokens_mean": 2.0, "latency_ms_mean": 612.167, "usd_sum": 0.002154 } }, { "task_id": "ogs:core:benchmark-task:vocab-007", "category": "vocabulary", "capability": "qualifier_vocabulary", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.qualifiers" ], "prompt_template_hash": "0adac8c06022acf5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nSelect the OGS aromatic qualifier that best describes how the item is expressed.\n\nINPUT:\n{\n \"item\": \"candied ginger\"\n}\n\nANSWER FORMAT: one_of:fresh,dried,cooked,candied,fermented,zest,overripe", "expected": { "value": "candied" }, "samples": [ { "sample": 0, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 299, "output_tokens": 2, "latency_ms": 568.9, "usd": 0.000614, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 299, "output_tokens": 2, "latency_ms": 623.2, "usd": 0.000614, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 299, "output_tokens": 2, "latency_ms": 649.2, "usd": 0.000614, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 299.0, "output_tokens_mean": 2.0, "latency_ms_mean": 613.767, "usd_sum": 0.001842 } }, { "task_id": "ogs:core:benchmark-task:vocab-008", "category": "vocabulary", "capability": "grade_scale", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.grade_scale" ], "prompt_template_hash": "e58319dc1276cdb2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n---\n\nUsing the OGS pairing grade scale (ogs-match.md §5), return the letter grade for the given overall score. Respond with just the grade token, e.g. 'A+'.\n\nINPUT:\n{\n \"overall_score\": 92\n}\n\nANSWER FORMAT: one_of:A+,A,B+,B,C+,C,D,F", "expected": { "value": "A" }, "samples": [ { "sample": 0, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 386, "output_tokens": 1, "latency_ms": 628.4, "usd": 0.00078, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 386, "output_tokens": 1, "latency_ms": 612.3, "usd": 0.00078, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 386, "output_tokens": 1, "latency_ms": 626.3, "usd": 0.00078, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 386.0, "output_tokens_mean": 1.0, "latency_ms_mean": 622.333, "usd_sum": 0.00234 } }, { "task_id": "ogs:core:benchmark-task:vocab-009", "category": "vocabulary", "capability": "aromatic_family_classification", "difficulty": "easy", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "d51864ab27ecfa64", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nUsing the OGS sensory model, return the single aromatic family that best characterises smoked paprika. Respond with just the family name.\n\nINPUT:\n{\n \"item\": \"smoked paprika (pimentón de la Vera)\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "spice" }, "samples": [ { "sample": 0, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 2, "latency_ms": 754.6, "usd": 0.00068, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 2, "latency_ms": 557.9, "usd": 0.00068, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 2, "latency_ms": 727.5, "usd": 0.00068, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 332.0, "output_tokens_mean": 2.0, "latency_ms_mean": 680.0, "usd_sum": 0.00204 } }, { "task_id": "ogs:core:benchmark-task:vocab-010", "category": "vocabulary", "capability": "aromatic_family_classification", "difficulty": "medium", "cuisine_region": "japanese", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "1748069ad0ebdde7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nUsing the OGS sensory model, return the single dominant aromatic family of a classic kombu-katsuo dashi.\n\nINPUT:\n{\n \"item\": \"classic kombu-katsuobushi dashi\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "marine" }, "samples": [ { "sample": 0, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 1, "latency_ms": 539.0, "usd": 0.000666, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 1, "latency_ms": 1193.5, "usd": 0.000666, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 1, "latency_ms": 652.5, "usd": 0.000666, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 329.0, "output_tokens_mean": 1.0, "latency_ms_mean": 795.0, "usd_sum": 0.001998 } }, { "task_id": "ogs:core:benchmark-task:vocab-011", "category": "vocabulary", "capability": "cooking_method_vocabulary", "difficulty": "easy", "cuisine_region": "indian", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "85de6add5c1ebfba", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nPick the single OGS cooking method that best matches tandoori chicken cooked at 450°C in a clay oven.\n\nINPUT:\n{\n \"description\": \"tandoori chicken, marinated and cooked in a clay tandoor at ~450°C\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "roasted" }, "samples": [ { "sample": 0, "raw_response": "grilled", "compliant": true, "score": 0.0, "detail": { "predicted": "grilled", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 399, "output_tokens": 2, "latency_ms": 620.6, "usd": 0.000814, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "grilled", "compliant": true, "score": 0.0, "detail": { "predicted": "grilled", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 399, "output_tokens": 2, "latency_ms": 633.2, "usd": 0.000814, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "grilled", "compliant": true, "score": 0.0, "detail": { "predicted": "grilled", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 399, "output_tokens": 2, "latency_ms": 588.6, "usd": 0.000814, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 399.0, "output_tokens_mean": 2.0, "latency_ms_mean": 614.133, "usd_sum": 0.002442 } }, { "task_id": "ogs:core:benchmark-task:vocab-012", "category": "vocabulary", "capability": "cooking_method_vocabulary", "difficulty": "medium", "cuisine_region": "peruvian", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "44c9b26dc70c4557", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nPick the single OGS cooking method that best describes Peruvian ceviche's treatment of white fish in lime juice.\n\nINPUT:\n{\n \"description\": \"diced white fish denatured in freshly squeezed lime juice for 10 minutes with red onion and aji limo\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "cured" }, "samples": [ { "sample": 0, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 2, "latency_ms": 621.9, "usd": 0.00082, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 2, "latency_ms": 569.2, "usd": 0.00082, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 2, "latency_ms": 630.2, "usd": 0.00082, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 402.0, "output_tokens_mean": 2.0, "latency_ms_mean": 607.1, "usd_sum": 0.00246 } }, { "task_id": "ogs:core:benchmark-task:vocab-013", "category": "vocabulary", "capability": "component_role_vocabulary", "difficulty": "medium", "cuisine_region": "moroccan", "scorer": "exact_match", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "dc3e62daf8bdf21a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nReturn the single OGS component role that best fits harissa stirred into a lamb tagine at service.\n\nINPUT:\n{\n \"description\": \"a spoonful of fiery harissa stirred into a lamb-and-apricot tagine at service\"\n}\n\nANSWER FORMAT: one_of:main_protein,main_vegetable,starch,sauce,fat_component,acid_component,aromatic_garnish,seasoning,textural_element", "expected": { "value": "seasoning" }, "samples": [ { "sample": 0, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 2, "latency_ms": 595.2, "usd": 0.00071, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "sauce", "compliant": true, "score": 0.0, "detail": { "predicted": "sauce", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 2, "latency_ms": 812.8, "usd": 0.00071, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "sauce", "compliant": true, "score": 0.0, "detail": { "predicted": "sauce", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 2, "latency_ms": 539.6, "usd": 0.00071, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.5774, "sem": 0.3333, "ci95_lo": -0.32, "ci95_hi": 0.9867, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 347.0, "output_tokens_mean": 2.0, "latency_ms_mean": 649.2, "usd_sum": 0.00213 } }, { "task_id": "ogs:core:benchmark-task:vocab-014", "category": "vocabulary", "capability": "qualifier_vocabulary", "difficulty": "medium", "cuisine_region": "chinese", "scorer": "exact_match", "context_needs": [ "vocab.qualifiers" ], "prompt_template_hash": "3980456a47e9b7c6", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nSelect the OGS aromatic qualifier that best describes the state of Sichuan peppercorn as it is commonly used — whole, toasted, and ground over finished mapo tofu.\n\nINPUT:\n{\n \"item\": \"Sichuan peppercorn (Zanthoxylum), whole, pan-toasted just before grinding over the dish\"\n}\n\nANSWER FORMAT: one_of:fresh,dried,cooked,candied,fermented,zest,overripe", "expected": { "value": "dried" }, "samples": [ { "sample": 0, "raw_response": "cooked", "compliant": true, "score": 0.0, "detail": { "predicted": "cooked", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 337, "output_tokens": 2, "latency_ms": 716.7, "usd": 0.00069, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cooked", "compliant": true, "score": 0.0, "detail": { "predicted": "cooked", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 337, "output_tokens": 2, "latency_ms": 950.9, "usd": 0.00069, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cooked", "compliant": true, "score": 0.0, "detail": { "predicted": "cooked", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 337, "output_tokens": 2, "latency_ms": 633.0, "usd": 0.00069, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 337.0, "output_tokens_mean": 2.0, "latency_ms_mean": 766.867, "usd_sum": 0.00207 } }, { "task_id": "ogs:core:benchmark-task:vocab-015", "category": "vocabulary", "capability": "grade_scale", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.grade_scale" ], "prompt_template_hash": "ad313a98974d64f7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n---\n\nUsing the OGS pairing grade scale, return the letter grade for a pairing whose `overall_score` is 78.\n\nINPUT:\n{\n \"overall_score\": 78\n}\n\nANSWER FORMAT: one_of:A+,A,B+,B,C+,C,D,F", "expected": { "value": "C+" }, "samples": [ { "sample": 0, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 372, "output_tokens": 2, "latency_ms": 603.2, "usd": 0.00076, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 372, "output_tokens": 2, "latency_ms": 683.2, "usd": 0.00076, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 372, "output_tokens": 2, "latency_ms": 592.7, "usd": 0.00076, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 372.0, "output_tokens_mean": 2.0, "latency_ms_mean": 626.367, "usd_sum": 0.00228 } }, { "task_id": "ogs:core:benchmark-task:vocab-016", "category": "vocabulary", "capability": "match_type_vocabulary", "difficulty": "medium", "cuisine_region": "british", "scorer": "exact_match", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "95e41ab82cba029a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nSelect the single OGS match type that best describes a beverage whose carbonation physically scrubs the palate between bites of a rich fried dish.\n\nINPUT:\n{\n \"description\": \"Champagne cleanses the palate between bites of fish and chips\"\n}\n\nANSWER FORMAT: one_of:harmony,contrast,bridge,intensity_alignment,structural_balance,refresh", "expected": { "value": "refresh" }, "samples": [ { "sample": 0, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 314, "output_tokens": 1, "latency_ms": 1436.6, "usd": 0.000636, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 314, "output_tokens": 1, "latency_ms": 852.6, "usd": 0.000636, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 314, "output_tokens": 1, "latency_ms": 810.1, "usd": 0.000636, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 314.0, "output_tokens_mean": 1.0, "latency_ms_mean": 1033.1, "usd_sum": 0.001908 } }, { "task_id": "ogs:core:benchmark-task:vocab-017", "category": "vocabulary", "capability": "aromatic_family_classification", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "8070fb687fd2f108", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nUsing the OGS sensory model, return the single dominant aromatic family of fresh cilantro leaves.\n\nINPUT:\n{\n \"item\": \"fresh cilantro / coriander leaves\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "herbal" }, "samples": [ { "sample": 0, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 319, "output_tokens": 2, "latency_ms": 710.2, "usd": 0.000654, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 319, "output_tokens": 2, "latency_ms": 773.5, "usd": 0.000654, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 319, "output_tokens": 2, "latency_ms": 827.3, "usd": 0.000654, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 319.0, "output_tokens_mean": 2.0, "latency_ms_mean": 770.333, "usd_sum": 0.001962 } }, { "task_id": "ogs:core:benchmark-task:vocab-018", "category": "vocabulary", "capability": "component_role_vocabulary", "difficulty": "medium", "cuisine_region": "levantine", "scorer": "exact_match", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "9e97b59361dbdf0e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nReturn the single OGS component role that best fits a drizzle of pomegranate molasses dressed onto a fattoush salad.\n\nINPUT:\n{\n \"description\": \"pomegranate molasses drizzled over a fattoush salad at service\"\n}\n\nANSWER FORMAT: one_of:main_protein,main_vegetable,starch,sauce,fat_component,acid_component,aromatic_garnish,seasoning,textural_element", "expected": { "value": "acid_component" }, "samples": [ { "sample": 0, "raw_response": "acid_component", "compliant": true, "score": 1.0, "detail": { "predicted": "acid_component", "expected": "acid_component", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 2, "latency_ms": 627.7, "usd": 0.00071, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "acid_component", "compliant": true, "score": 1.0, "detail": { "predicted": "acid_component", "expected": "acid_component", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 2, "latency_ms": 807.6, "usd": 0.00071, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "acid_component", "compliant": true, "score": 1.0, "detail": { "predicted": "acid_component", "expected": "acid_component", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 2, "latency_ms": 739.0, "usd": 0.00071, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 347.0, "output_tokens_mean": 2.0, "latency_ms_mean": 724.767, "usd_sum": 0.00213 } }, { "task_id": "ogs:core:benchmark-task:vocab-019", "category": "vocabulary", "capability": "cooking_method_vocabulary", "difficulty": "medium", "cuisine_region": "filipino", "scorer": "exact_match", "context_needs": [ "vocab.cooking_methods" ], "prompt_template_hash": "fc9a763682f1225b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n---\n\nPick the single OGS cooking method that best describes bagoong alamang (Philippine fermented salt-cured shrimp paste).\n\nINPUT:\n{\n \"description\": \"bagoong alamang: salt-cured tiny shrimp left to ferment for 3-6 months\"\n}\n\nANSWER FORMAT: one_of:raw,seared,grilled,roasted,braised,poached,steamed,fried,confit,smoked,fermented,cured,pickled,dehydrated,sous_vide,blanched,sauteed,baked,charred,emulsified", "expected": { "value": "fermented" }, "samples": [ { "sample": 0, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 401, "output_tokens": 2, "latency_ms": 610.8, "usd": 0.000818, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 401, "output_tokens": 2, "latency_ms": 687.1, "usd": 0.000818, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 401, "output_tokens": 2, "latency_ms": 594.3, "usd": 0.000818, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 401.0, "output_tokens_mean": 2.0, "latency_ms_mean": 630.733, "usd_sum": 0.002454 } }, { "task_id": "ogs:core:benchmark-task:vocab-020", "category": "vocabulary", "capability": "grade_scale", "difficulty": "medium", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "vocab.grade_scale" ], "prompt_template_hash": "56ad4f9c58bc1eb7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n---\n\nUsing the OGS pairing grade scale, return the letter grade for a pairing whose `overall_score` is 64.\n\nINPUT:\n{\n \"overall_score\": 64\n}\n\nANSWER FORMAT: one_of:A+,A,B+,B,C+,C,D,F", "expected": { "value": "D" }, "samples": [ { "sample": 0, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 372, "output_tokens": 1, "latency_ms": 768.1, "usd": 0.000752, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 372, "output_tokens": 1, "latency_ms": 600.2, "usd": 0.000752, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 372, "output_tokens": 1, "latency_ms": 723.3, "usd": 0.000752, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 372.0, "output_tokens_mean": 1.0, "latency_ms_mean": 697.2, "usd_sum": 0.002256 } }, { "task_id": "ogs:core:benchmark-task:xplain-001", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "a75ad0ee2a385794", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nFrom the OGS explanation-code vocabulary, return the set of codes that best explain WHY the pairing below is excellent. Respond as a JSON array of code IDs. Pick 3 to 6 most relevant positive codes.\n\nINPUT:\n{\n \"dish\": \"A5 wagyu with black truffle jus (very rich, high umami, earthy aromatics, full body)\",\n \"beverage\": \"Barolo 2018 (Nebbiolo, high tannin, high acidity, full body, tar/forest-floor)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_FAT", "STRUCT_INTENSITY_MATCH", "AROMA_SHARED_EARTH", "STRUCT_BODY_ALIGN", "HARMONY_FLAVOR_CONVERGE" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"STRUCT_BODY_ALIGN\",\n \"STRUCT_UMAMI_ENHANCE\"\n]", "compliant": true, "score": 0.7273, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "precision": 0.6667, "recall": 0.8 }, "metrics": { "input_tokens": 1159, "output_tokens": 57, "latency_ms": 899.1, "usd": 0.002774, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_EARTH\",\"STRUCT_TANNIN_FAT\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_BODY_ALIGN\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1159, "output_tokens": 35, "latency_ms": 880.6, "usd": 0.002598, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\", \"HARMONY_FLAVOR_CONVERGE\", \"STRUCT_TANNIN_FAT\", \"STRUCT_INTENSITY_MATCH\", \"STRUCT_BODY_ALIGN\", \"REFRESH_ACID\"]", "compliant": true, "score": 0.9091, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "precision": 0.8333, "recall": 1.0 }, "metrics": { "input_tokens": 1159, "output_tokens": 44, "latency_ms": 700.1, "usd": 0.00267, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7455, "score_summary": { "mean": 0.7455, "stdev": 0.1553, "sem": 0.0897, "ci95_lo": 0.5697, "ci95_hi": 0.9213, "n": 3 }, "score_if_valid": 0.7455, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1159.0, "output_tokens_mean": 45.333, "latency_ms_mean": 826.6, "usd_sum": 0.008042 } }, { "task_id": "ogs:core:benchmark-task:xplain-002", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "bdc5d8d74c85e9ab", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain the success of the pairing below. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"fresh oysters on the half shell with lemon\",\n \"beverage\": \"Chablis Premier Cru (Chardonnay, high acid, mineral, lean body)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_ACIDITY_BALANCE", "REFRESH_ACID", "REFRESH_MINERAL", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_EARTH\",\"AROMA_SHARED_FRUIT\",\"REFRESH_ACID\",\"REFRESH_MINERAL\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.4, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_FRUIT", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.4, "recall": 0.4 }, "metrics": { "input_tokens": 1124, "output_tokens": 30, "latency_ms": 849.8, "usd": 0.002488, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_MINERAL\",\n \"STRUCT_BODY_ALIGN\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1124, "output_tokens": 41, "latency_ms": 715.6, "usd": 0.002576, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"AROMA_SHARED_EARTH\",\n \"AROMA_SHARED_FRUIT\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_MINERAL\",\n \"STRUCT_BODY_ALIGN\"\n]", "compliant": true, "score": 0.4, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_FRUIT", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.4, "recall": 0.4 }, "metrics": { "input_tokens": 1124, "output_tokens": 41, "latency_ms": 1002.6, "usd": 0.002576, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.4667, "score_summary": { "mean": 0.4667, "stdev": 0.1155, "sem": 0.0667, "ci95_lo": 0.336, "ci95_hi": 0.5973, "n": 3 }, "score_if_valid": 0.4667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1124.0, "output_tokens_mean": 37.333, "latency_ms_mean": 856.0, "usd_sum": 0.00764 } }, { "task_id": "ogs:core:benchmark-task:xplain-003", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "3440bcf3978a1c58", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (2 to 4 codes).\n\nINPUT:\n{\n \"dish\": \"crispy buttermilk fried chicken\",\n \"beverage\": \"non-vintage Brut Champagne\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "REFRESH_EFFERVESCE", "REFRESH_ACID", "CONTRAST_RICH_CRISP" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"REFRESH_EFFERVESCE\",\n \"REFRESH_ACID\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.75, "recall": 1.0 }, "metrics": { "input_tokens": 1111, "output_tokens": 37, "latency_ms": 888.5, "usd": 0.002518, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"REFRESH_EFFERVESCE\",\n \"REFRESH_ACID\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.75, "recall": 1.0 }, "metrics": { "input_tokens": 1111, "output_tokens": 37, "latency_ms": 914.6, "usd": 0.002518, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"CONTRAST_RICH_CRISP\", \"REFRESH_EFFERVESCE\", \"STRUCT_INTENSITY_MATCH\", \"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.5714, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.5, "recall": 0.6667 }, "metrics": { "input_tokens": 1111, "output_tokens": 30, "latency_ms": 831.3, "usd": 0.002462, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7619, "score_summary": { "mean": 0.7619, "stdev": 0.1649, "sem": 0.0952, "ci95_lo": 0.5752, "ci95_hi": 0.9485, "n": 3 }, "score_if_valid": 0.7619, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1111.0, "output_tokens_mean": 34.667, "latency_ms_mean": 878.133, "usd_sum": 0.007498 } }, { "task_id": "ogs:core:benchmark-task:xplain-004", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "b3249dafda966f70", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain the success of the pairing below. Respond as a JSON array (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"seared foie gras on brioche (very rich, fatty, slightly sweet-savoury)\",\n \"beverage\": \"Sauternes (botrytised sweet white, high residual sugar, high acidity)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "STRUCT_ACIDITY_BALANCE", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"STRUCT_SWEET_OFFSET\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_FLAVOR_CONVERGE", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1131, "output_tokens": 48, "latency_ms": 828.4, "usd": 0.002646, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"CONTRAST_SWEET_ACID\",\n \"STRUCT_SWEET_OFFSET\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "CONTRAST_SWEET_ACID", "HARMONY_FLAVOR_CONVERGE", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1131, "output_tokens": 49, "latency_ms": 903.8, "usd": 0.002654, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"CONTRAST_SWEET_ACID\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1131, "output_tokens": 31, "latency_ms": 1523.0, "usd": 0.00251, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.4444, "score_summary": { "mean": 0.4444, "stdev": 0.2223, "sem": 0.1283, "ci95_lo": 0.1929, "ci95_hi": 0.6959, "n": 3 }, "score_if_valid": 0.4444, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1131.0, "output_tokens_mean": 42.667, "latency_ms_mean": 1085.067, "usd_sum": 0.00781 } }, { "task_id": "ogs:core:benchmark-task:xplain-005", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "0cb2f1946943a0e2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain why the pairing works. Respond as a JSON array (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"charcoal-grilled lamb rack with rosemary, black pepper crust, charred edges\",\n \"beverage\": \"Northern Rhone Syrah (Cote-Rotie) — black pepper, violet, smoked meat, moderate-high tannin\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "AROMA_SHARED_HERBAL", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"AROMA_SHARED_SPICE\",\n \"AROMA_SHARED_EARTH\",\n \"AROMA_SHARED_WOOD\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1136, "output_tokens": 45, "latency_ms": 823.3, "usd": 0.002632, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_SPICE\", \"AROMA_SHARED_WOOD\", \"STRUCT_TANNIN_PROTEIN\", \"STRUCT_BODY_ALIGN\", \"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1136, "output_tokens": 37, "latency_ms": 863.6, "usd": 0.002568, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_SPICE\", \"AROMA_SHARED_EARTH\", \"AROMA_SHARED_WOOD\", \"STRUCT_TANNIN_PROTEIN\", \"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1136, "output_tokens": 36, "latency_ms": 873.0, "usd": 0.00256, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6, "score_summary": { "mean": 0.6, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.6, "ci95_hi": 0.6, "n": 3 }, "score_if_valid": 0.6, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1136.0, "output_tokens_mean": 39.333, "latency_ms_mean": 853.3, "usd_sum": 0.00776 } }, { "task_id": "ogs:core:benchmark-task:xplain-006", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "9a46b0d141442ce3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"Pizza Margherita (tomato, mozzarella, basil)\",\n \"beverage\": \"Chianti Classico (Sangiovese, high acid, medium tannin)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_ACIDITY_BALANCE", "HARMONY_REGIONAL", "STRUCT_INTENSITY_MATCH", "AROMA_SHARED_HERBAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"AROMA_SHARED_EARTH\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1127, "output_tokens": 34, "latency_ms": 654.9, "usd": 0.002526, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_HERBAL\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1127, "output_tokens": 45, "latency_ms": 1018.1, "usd": 0.002614, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_HERBAL\", \"STRUCT_ACIDITY_BALANCE\", \"STRUCT_INTENSITY_MATCH\", \"STRUCT_TANNIN_PROTEIN\", \"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1127, "output_tokens": 39, "latency_ms": 618.9, "usd": 0.002566, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.8889, "score_summary": { "mean": 0.8889, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.8889, "ci95_hi": 0.8889, "n": 3 }, "score_if_valid": 0.8889, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1127.0, "output_tokens_mean": 39.333, "latency_ms_mean": 763.967, "usd_sum": 0.007706 } }, { "task_id": "ogs:core:benchmark-task:xplain-007", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "chinese", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "497adc64f3303eb4", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"mapo tofu with Sichuan peppercorn\",\n \"beverage\": \"off-dry German Spätlese Riesling\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "CONTRAST_SWEET_SALTY" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"AROMA_SHARED_SPICE\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1118, "output_tokens": 45, "latency_ms": 810.4, "usd": 0.002596, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"AROMA_SHARED_SPICE\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1118, "output_tokens": 37, "latency_ms": 841.8, "usd": 0.002532, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"AROMA_SHARED_FRUIT\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1118, "output_tokens": 45, "latency_ms": 772.3, "usd": 0.002596, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.8426, "score_summary": { "mean": 0.8426, "stdev": 0.0802, "sem": 0.0463, "ci95_lo": 0.7519, "ci95_hi": 0.9333, "n": 3 }, "score_if_valid": 0.8426, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1118.0, "output_tokens_mean": 42.333, "latency_ms_mean": 808.167, "usd_sum": 0.007724 } }, { "task_id": "ogs:core:benchmark-task:xplain-008", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "2120f96a0444a50e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"herb-crusted rack of lamb, medium-rare\",\n \"beverage\": \"Northern Rhône Syrah\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_PROTEIN", "AROMA_SHARED_HERBAL", "STRUCT_BODY_ALIGN", "HARMONY_FLAVOR_CONVERGE" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_HERBAL\", \"AROMA_SHARED_EARTH\", \"STRUCT_TANNIN_PROTEIN\", \"STRUCT_INTENSITY_MATCH\", \"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1115, "output_tokens": 42, "latency_ms": 790.3, "usd": 0.002566, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_HERBAL\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1115, "output_tokens": 49, "latency_ms": 899.5, "usd": 0.002622, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"AROMA_SHARED_EARTH\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1115, "output_tokens": 33, "latency_ms": 837.1, "usd": 0.002494, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.6667, "ci95_hi": 0.6667, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1115.0, "output_tokens_mean": 41.333, "latency_ms_mean": 842.3, "usd_sum": 0.007682 } }, { "task_id": "ogs:core:benchmark-task:xplain-009", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "thai", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "c077c498ceed5f73", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"Thai green curry with chicken and Thai basil\",\n \"beverage\": \"off-dry New Zealand Sauvignon Blanc\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"AROMA_SHARED_HERBAL\",\n \"CONTRAST_SWEET_ACID\",\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1115, "output_tokens": 48, "latency_ms": 1241.1, "usd": 0.002614, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_HERBAL\",\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1115, "output_tokens": 34, "latency_ms": 795.5, "usd": 0.002502, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"AROMA_SHARED_HERBAL\",\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_SWEET_OFFSET\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_ACID\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1115, "output_tokens": 47, "latency_ms": 779.0, "usd": 0.002606, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7778, "score_summary": { "mean": 0.7778, "stdev": 0.1924, "sem": 0.1111, "ci95_lo": 0.56, "ci95_hi": 0.9956, "n": 3 }, "score_if_valid": 0.7778, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1115.0, "output_tokens_mean": 43.0, "latency_ms_mean": 938.533, "usd_sum": 0.007722 } }, { "task_id": "ogs:core:benchmark-task:xplain-010", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "easy", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "956c6ce654c2e297", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"moules marinières\",\n \"beverage\": \"Muscadet sur lie\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_ACIDITY_BALANCE", "REFRESH_ACID", "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_MINERAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_EARTH\",\"AROMA_SHARED_HERBAL\",\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_MINERAL\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 1111, "output_tokens": 33, "latency_ms": 681.7, "usd": 0.002486, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"HARMONY_REGIONAL\", \"AROMA_SHARED_EARTH\", \"STRUCT_ACIDITY_BALANCE\", \"REFRESH_MINERAL\", \"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1111, "output_tokens": 36, "latency_ms": 778.0, "usd": 0.00251, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\",\"HARMONY_REGIONAL\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.5, "recall": 0.4 }, "metrics": { "input_tokens": 1111, "output_tokens": 25, "latency_ms": 789.1, "usd": 0.002422, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6148, "score_summary": { "mean": 0.6148, "stdev": 0.1783, "sem": 0.1029, "ci95_lo": 0.4131, "ci95_hi": 0.8165, "n": 3 }, "score_if_valid": 0.6148, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1111.0, "output_tokens_mean": 31.333, "latency_ms_mean": 749.6, "usd_sum": 0.007418 } }, { "task_id": "ogs:core:benchmark-task:xplain-011", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "mexican", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "1dfeb782059a4814", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"tacos al pastor with pineapple and chili\",\n \"beverage\": \"dry sparkling rosé (Cava rosado)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "REFRESH_EFFERVESCE", "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"AROMA_SHARED_FRUIT\",\n \"CONTRAST_SWEET_ACID\",\n \"STRUCT_INTENSITY_MATCH\",\n \"REFRESH_EFFERVESCE\",\n \"REFRESH_ACID\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1117, "output_tokens": 46, "latency_ms": 889.4, "usd": 0.002602, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_FRUIT\",\n \"CONTRAST_SWEET_ACID\",\n \"REFRESH_EFFERVESCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_ACIDITY_BALANCE\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_ACID", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1117, "output_tokens": 48, "latency_ms": 961.0, "usd": 0.002618, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"AROMA_SHARED_SPICE\",\"STRUCT_INTENSITY_MATCH\",\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "AROMA_SHARED_SPICE", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1117, "output_tokens": 32, "latency_ms": 737.4, "usd": 0.00249, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.4444, "score_summary": { "mean": 0.4444, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.4444, "ci95_hi": 0.4444, "n": 3 }, "score_if_valid": 0.4444, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1117.0, "output_tokens_mean": 42.0, "latency_ms_mean": 862.6, "usd_sum": 0.00771 } }, { "task_id": "ogs:core:benchmark-task:xplain-012", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "28df36c8ae155697", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"duck confit, crispy skin\",\n \"beverage\": \"mature Burgundy Pinot Noir (10 years)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_FAT", "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "HARMONY_COMPLEXITY_MATCH" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"AROMA_SHARED_EARTH\",\n \"AROMA_SHARED_SPICE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_TANNIN_FAT\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_SPICE", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1114, "output_tokens": 47, "latency_ms": 902.2, "usd": 0.002604, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"HARMONY_FLAVOR_CONVERGE\", \"AROMA_SHARED_EARTH\", \"STRUCT_TANNIN_FAT\", \"STRUCT_INTENSITY_MATCH\", \"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1114, "output_tokens": 38, "latency_ms": 799.2, "usd": 0.002532, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\",\"AROMA_SHARED_FRUIT\",\"STRUCT_TANNIN_FAT\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1114, "output_tokens": 35, "latency_ms": 705.8, "usd": 0.002508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.5185, "score_summary": { "mean": 0.5185, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.3733, "ci95_hi": 0.6637, "n": 3 }, "score_if_valid": 0.5185, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1114.0, "output_tokens_mean": 40.0, "latency_ms_mean": 802.4, "usd_sum": 0.007644 } }, { "task_id": "ogs:core:benchmark-task:xplain-013", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "spanish", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "18a20e7e30844c41", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"jamón ibérico de bellota, sliced thin\",\n \"beverage\": \"chilled Fino sherry (Manzanilla)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_UMAMI_ENHANCE", "HARMONY_REGIONAL", "AROMA_SHARED_SAVORY", "REFRESH_MINERAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_NUT\", \"CONTRAST_RICH_CRISP\", \"STRUCT_INTENSITY_MATCH\", \"REFRESH_ACID\", \"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_NUT", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1120, "output_tokens": 36, "latency_ms": 1117.3, "usd": 0.002528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_NUTTY\",\"CONTRAST_RICH_CRISP\",\"STRUCT_INTENSITY_MATCH\",\"REFRESH_ACID\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_NUTTY", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1120, "output_tokens": 33, "latency_ms": 803.0, "usd": 0.002504, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"AROMA_SHARED_NUTTY\",\n \"AROMA_SHARED_SALINE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_BODY_ALIGN\",\n \"REFRESH_ACID\"\n]", "compliant": true, "score": 0.0, "detail": { "predicted": [ "AROMA_SHARED_NUTTY", "AROMA_SHARED_SALINE", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.0, "recall": 0.0 }, "metrics": { "input_tokens": 1120, "output_tokens": 41, "latency_ms": 923.1, "usd": 0.002568, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.1481, "score_summary": { "mean": 0.1481, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.003, "ci95_hi": 0.2933, "n": 3 }, "score_if_valid": 0.1481, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1120.0, "output_tokens_mean": 36.667, "latency_ms_mean": 947.8, "usd_sum": 0.0076 } }, { "task_id": "ogs:core:benchmark-task:xplain-014", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "korean", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "f9be4ef2853d67b3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"bulgogi: soy-pear-garlic marinated grilled beef\",\n \"beverage\": \"medium-bodied unoaked Merlot\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_PROTEIN", "STRUCT_SWEET_OFFSET", "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_FRUIT\", \"AROMA_SHARED_SPICE\", \"STRUCT_BODY_ALIGN\", \"STRUCT_TANNIN_FAT\", \"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "AROMA_SHARED_SPICE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1120, "output_tokens": 34, "latency_ms": 763.9, "usd": 0.002512, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_FRUIT\", \"AROMA_SHARED_EARTH\", \"STRUCT_INTENSITY_MATCH\", \"STRUCT_BODY_ALIGN\", \"STRUCT_TANNIN_PROTEIN\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1120, "output_tokens": 36, "latency_ms": 863.4, "usd": 0.002528, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\", \"AROMA_SHARED_SPICE\", \"STRUCT_INTENSITY_MATCH\", \"STRUCT_BODY_ALIGN\", \"STRUCT_TANNIN_PROTEIN\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "AROMA_SHARED_SPICE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1120, "output_tokens": 35, "latency_ms": 987.4, "usd": 0.00252, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.5926, "score_summary": { "mean": 0.5926, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.4474, "ci95_hi": 0.7378, "n": 3 }, "score_if_valid": 0.5926, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1120.0, "output_tokens_mean": 35.0, "latency_ms_mean": 871.567, "usd_sum": 0.00756 } }, { "task_id": "ogs:core:benchmark-task:xplain-015", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "easy", "cuisine_region": "british", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "5474f731e5d9751c", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"Stilton blue cheese\",\n \"beverage\": \"Vintage Port\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "CONTRAST_SWEET_SALTY", "STRUCT_INTENSITY_MATCH", "HARMONY_COMPLEXITY_MATCH", "STRUCT_SWEET_OFFSET" ] }, "samples": [ { "sample": 0, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1107, "output_tokens": 32, "latency_ms": 743.7, "usd": 0.00247, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"CONTRAST_SWEET_SALTY\",\"AROMA_SHARED_FRUIT\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1107, "output_tokens": 33, "latency_ms": 1209.4, "usd": 0.002478, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_SWEET_OFFSET\",\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1107, "output_tokens": 41, "latency_ms": 844.1, "usd": 0.002542, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.7222, "score_summary": { "mean": 0.7222, "stdev": 0.0481, "sem": 0.0278, "ci95_lo": 0.6678, "ci95_hi": 0.7767, "n": 3 }, "score_if_valid": 0.7222, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1107.0, "output_tokens_mean": 35.333, "latency_ms_mean": 932.4, "usd_sum": 0.00749 } }, { "task_id": "ogs:core:benchmark-task:xplain-016", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "fc7f227aebed6756", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"shrimp tempura, light fry\",\n \"beverage\": \"chilled junmai ginjo sake\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_UMAMI_ENHANCE", "REFRESH_MINERAL", "AROMA_SHARED_FLORAL", "STRUCT_INTENSITY_MATCH", "HARMONY_REGIONAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.4, "detail": { "predicted": [ "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.4 }, "metrics": { "input_tokens": 1114, "output_tokens": 31, "latency_ms": 733.1, "usd": 0.002476, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"STRUCT_BODY_ALIGN\", \"STRUCT_INTENSITY_MATCH\", \"REFRESH_ACID\", \"AROMA_SHARED_FRUIT\", \"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.2, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.2, "recall": 0.2 }, "metrics": { "input_tokens": 1114, "output_tokens": 35, "latency_ms": 833.7, "usd": 0.002508, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"REFRESH_ACID\", \"HARMONY_FLAVOR_CONVERGE\", \"STRUCT_BODY_ALIGN\", \"REFRESH_MINERAL\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_BODY_ALIGN" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.25, "recall": 0.2 }, "metrics": { "input_tokens": 1114, "output_tokens": 27, "latency_ms": 740.9, "usd": 0.002444, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.2741, "score_summary": { "mean": 0.2741, "stdev": 0.1096, "sem": 0.0633, "ci95_lo": 0.15, "ci95_hi": 0.3981, "n": 3 }, "score_if_valid": 0.2741, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1114.0, "output_tokens_mean": 31.0, "latency_ms_mean": 769.233, "usd_sum": 0.007428 } }, { "task_id": "ogs:core:benchmark-task:xplain-017", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "greek", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "024198497e327bb1", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"horiatiki salad with feta, tomato, olive, oregano\",\n \"beverage\": \"Santorini Assyrtiko\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "REFRESH_ACID", "REFRESH_MINERAL", "HARMONY_REGIONAL", "AROMA_SHARED_HERBAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_HERBAL\", \"AROMA_SHARED_EARTH\", \"HARMONY_REGIONAL\", \"STRUCT_ACIDITY_BALANCE\", \"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1119, "output_tokens": 37, "latency_ms": 774.0, "usd": 0.002534, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_HERBAL\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"HARMONY_REGIONAL\",\n \"REFRESH_MINERAL\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1119, "output_tokens": 44, "latency_ms": 939.1, "usd": 0.00259, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"AROMA_SHARED_HERBAL\",\n \"AROMA_SHARED_EARTH\",\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_ACID\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1119, "output_tokens": 44, "latency_ms": 879.7, "usd": 0.00259, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.6667, "ci95_hi": 0.6667, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1119.0, "output_tokens_mean": 41.667, "latency_ms_mean": 864.267, "usd_sum": 0.007714 } }, { "task_id": "ogs:core:benchmark-task:xplain-018", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "chinese", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "283bbb9e703e6e30", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"Peking duck with pancake, scallion, hoisin\",\n \"beverage\": \"10-year-old off-dry Mosel Riesling\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "AROMA_SHARED_FRUIT", "REFRESH_ACID", "HARMONY_COMPLEXITY_MATCH" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_FRUIT\", \"CONTRAST_RICH_CRISP\", \"STRUCT_SWEET_OFFSET\", \"STRUCT_ACIDITY_BALANCE\", \"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "HARMONY_COMPLEXITY_MATCH", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1121, "output_tokens": 40, "latency_ms": 838.8, "usd": 0.002562, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_RICH_CRISP\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1121, "output_tokens": 32, "latency_ms": 824.9, "usd": 0.002498, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"STRUCT_SWEET_OFFSET\", \"AROMA_SHARED_FRUIT\", \"STRUCT_ACIDITY_BALANCE\", \"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1121, "output_tokens": 31, "latency_ms": 1425.3, "usd": 0.00249, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.6945, "score_summary": { "mean": 0.6945, "stdev": 0.0481, "sem": 0.0278, "ci95_lo": 0.64, "ci95_hi": 0.7489, "n": 3 }, "score_if_valid": 0.6945, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1121.0, "output_tokens_mean": 34.333, "latency_ms_mean": 1029.667, "usd_sum": 0.00755 } }, { "task_id": "ogs:core:benchmark-task:xplain-019", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "9ea6cd79384f9ee2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"Sunday ragù napoletano (long-cooked beef and pork)\",\n \"beverage\": \"Campanian Aglianico, 5 years\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_PROTEIN", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "AROMA_SHARED_WOOD" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_EARTH\",\"AROMA_SHARED_SPICE\",\"STRUCT_TANNIN_FAT\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_SPICE", "HARMONY_REGIONAL", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1124, "output_tokens": 33, "latency_ms": 801.0, "usd": 0.002512, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_EARTH\",\n \"AROMA_SHARED_SPICE\",\n \"HARMONY_REGIONAL\",\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_SPICE", "HARMONY_REGIONAL", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1124, "output_tokens": 44, "latency_ms": 879.4, "usd": 0.0026, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_BODY_ALIGN\",\n \"AROMA_SHARED_EARTH\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1124, "output_tokens": 43, "latency_ms": 777.1, "usd": 0.002592, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.3704, "score_summary": { "mean": 0.3704, "stdev": 0.2566, "sem": 0.1482, "ci95_lo": 0.08, "ci95_hi": 0.6608, "n": 3 }, "score_if_valid": 0.3704, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1124.0, "output_tokens_mean": 40.0, "latency_ms_mean": 819.167, "usd_sum": 0.007704 } }, { "task_id": "ogs:core:benchmark-task:xplain-020", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "easy", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "43005f44c870684b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"foie gras torchon with brioche\",\n \"beverage\": \"Sauternes\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN" ] }, "samples": [ { "sample": 0, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"AROMA_SHARED_FRUIT\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1111, "output_tokens": 38, "latency_ms": 858.4, "usd": 0.002526, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"REFRESH_ACID\",\"AROMA_SHARED_FRUIT\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1111, "output_tokens": 34, "latency_ms": 723.0, "usd": 0.002494, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"CONTRAST_SWEET_SALTY\", \"STRUCT_SWEET_OFFSET\", \"STRUCT_INTENSITY_MATCH\", \"AROMA_SHARED_FRUIT\", \"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1111, "output_tokens": 42, "latency_ms": 1083.2, "usd": 0.002558, "model_version": "gpt-4.1-2025-04-14", "finish_reason": "stop" } } ], "score": 0.4444, "score_summary": { "mean": 0.4444, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.4444, "ci95_hi": 0.4444, "n": 3 }, "score_if_valid": 0.4444, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1111.0, "output_tokens_mean": 38.0, "latency_ms_mean": 888.2, "usd_sum": 0.007578 } } ], "category_scores": { "composition": { "mean_score": 0.8076, "ci95_lo": 0.6413, "ci95_hi": 0.974, "stdev": 0.3795, "task_count": 20, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.8076 }, "dietary": { "mean_score": 0.8214, "ci95_lo": 0.6487, "ci95_hi": 0.9942, "stdev": 0.3053, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.8214 }, "explanation": { "mean_score": 0.5843, "ci95_lo": 0.4996, "ci95_hi": 0.669, "stdev": 0.1933, "task_count": 20, "weight": 0.1, "format_rate": 1.0, "score_if_valid": 0.5843 }, "menu_engineering": { "mean_score": 1.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "stdev": 0.0, "task_count": 8, "weight": 0.03, "format_rate": 1.0, "score_if_valid": 1.0 }, "nutrition": { "mean_score": 0.5311, "ci95_lo": 0.2897, "ci95_hi": 0.7725, "stdev": 0.3895, "task_count": 10, "weight": 0.03, "format_rate": 1.0, "score_if_valid": 0.5311 }, "pairing": { "mean_score": 1.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "stdev": 0.0, "task_count": 22, "weight": 0.15, "format_rate": 1.0, "score_if_valid": 1.0 }, "regional": { "mean_score": 1.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "stdev": 0.0, "task_count": 24, "weight": 0.05, "format_rate": 1.0, "score_if_valid": 1.0 }, "risk": { "mean_score": 0.85, "ci95_lo": 0.6894, "ci95_hi": 1.0106, "stdev": 0.3663, "task_count": 20, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 0.85 }, "safety": { "mean_score": 0.8889, "ci95_lo": 0.7215, "ci95_hi": 1.0563, "stdev": 0.2959, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.8889 }, "sensory": { "mean_score": 0.6049, "ci95_lo": 0.4767, "ci95_hi": 0.7331, "stdev": 0.2997, "task_count": 21, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.6049 }, "structured_output": { "mean_score": 0.7667, "ci95_lo": 0.6087, "ci95_hi": 0.9246, "stdev": 0.3603, "task_count": 20, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.7667 }, "vocabulary": { "mean_score": 0.8551, "ci95_lo": 0.7199, "ci95_hi": 0.9902, "stdev": 0.3307, "task_count": 23, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 0.8551 } }, "aggregate": { "score": 80.49, "ci95_lo": 76.48, "ci95_hi": 84.5, "scale": "0-100", "partial": false, "missing_categories": [] }, "metrics": { "latency_ms_mean": 1060.241, "latency_ms_median": 691.333, "input_tokens_mean": 729.8, "output_tokens_mean": 66.4, "usd_total": 1.272388, "tasks_with_usd": 213 }, "weights": { "vocabulary": 0.08, "sensory": 0.12, "composition": 0.12, "pairing": 0.15, "explanation": 0.1, "risk": 0.08, "structured_output": 0.12, "regional": 0.05, "dietary": 0.06, "safety": 0.06, "nutrition": 0.03, "menu_engineering": 0.03 }, "judge": { "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false, "excluded_task_ids": [ "ogs:core:benchmark-task:menu-009" ], "note": "Rubric-judge tasks are scored and retained in `tasks`, but excluded from `aggregate` until the judge clears the human-validation protocol (r > 0.8 against a 50-task sample)." } }