{ "benchmark_version": "0.3.0", "ogs_version": "0.2.0", "run_id": "dbca1180-de2d-4759-afed-75c09b9bee4f", "run_at": "2026-04-18T06:10:52.587004+00:00", "model": { "id": "gpt-5.4-mini", "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": 408, "output_tokens": 4, "latency_ms": 613.7, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 408, "output_tokens": 4, "latency_ms": 632.6, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 408, "output_tokens": 4, "latency_ms": 835.2, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 408.0, "output_tokens_mean": 4.0, "latency_ms_mean": 693.833, "usd_sum": 0.00033 } }, { "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": 399, "output_tokens": 4, "latency_ms": 684.9, "usd": 0.000108, "model_version": "gpt-5.4-mini-2026-03-17", "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": 399, "output_tokens": 4, "latency_ms": 598.1, "usd": 0.000108, "model_version": "gpt-5.4-mini-2026-03-17", "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": 399, "output_tokens": 4, "latency_ms": 583.8, "usd": 0.000108, "model_version": "gpt-5.4-mini-2026-03-17", "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": 399.0, "output_tokens_mean": 4.0, "latency_ms_mean": 622.267, "usd_sum": 0.000324 } }, { "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": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 397, "output_tokens": 4, "latency_ms": 524.0, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 1387.9, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 501.8, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397.0, "output_tokens_mean": 4.0, "latency_ms_mean": 804.567, "usd_sum": 0.000321 } }, { "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": 431, "output_tokens": 5, "latency_ms": 643.0, "usd": 0.000118, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 431, "output_tokens": 5, "latency_ms": 669.0, "usd": 0.000118, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 431, "output_tokens": 5, "latency_ms": 605.8, "usd": 0.000118, "model_version": "gpt-5.4-mini-2026-03-17", "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": 431.0, "output_tokens_mean": 5.0, "latency_ms_mean": 639.267, "usd_sum": 0.000354 } }, { "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": 356, "output_tokens": 6, "latency_ms": 607.0, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 356, "output_tokens": 6, "latency_ms": 472.0, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 356, "output_tokens": 6, "latency_ms": 651.3, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 356.0, "output_tokens_mean": 6.0, "latency_ms_mean": 576.767, "usd_sum": 0.000303 } }, { "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\",\"seasoning\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "fat_component", "main_protein", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 0.8 }, "metrics": { "input_tokens": 467, "output_tokens": 17, "latency_ms": 469.9, "usd": 0.000151, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"main_protein\",\"starch\",\"fat_component\",\"seasoning\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "fat_component", "main_protein", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 0.8 }, "metrics": { "input_tokens": 467, "output_tokens": 17, "latency_ms": 834.6, "usd": 0.000151, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"main_protein\",\"starch\",\"fat_component\",\"seasoning\",\"sauce\"]", "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": 467, "output_tokens": 20, "latency_ms": 636.8, "usd": 0.000157, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.9259, "score_summary": { "mean": 0.9259, "stdev": 0.0641, "sem": 0.037, "ci95_lo": 0.8533, "ci95_hi": 0.9985, "n": 3 }, "score_if_valid": 0.9259, "format_rate": 1.0, "metrics": { "input_tokens_mean": 467.0, "output_tokens_mean": 18.0, "latency_ms_mean": 647.1, "usd_sum": 0.000459 } }, { "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": 312, "output_tokens": 4, "latency_ms": 592.3, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 312, "output_tokens": 4, "latency_ms": 795.2, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 312, "output_tokens": 4, "latency_ms": 575.2, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 312.0, "output_tokens_mean": 4.0, "latency_ms_mean": 654.233, "usd_sum": 0.000258 } }, { "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": 397, "output_tokens": 4, "latency_ms": 740.8, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 498.3, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 555.6, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 598.233, "usd_sum": 0.000321 } }, { "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": 397, "output_tokens": 4, "latency_ms": 558.4, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 479.2, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 615.4, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 551.0, "usd_sum": 0.000321 } }, { "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": 397, "output_tokens": 4, "latency_ms": 585.7, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 537.6, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397, "output_tokens": 4, "latency_ms": 557.3, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 397.0, "output_tokens_mean": 4.0, "latency_ms_mean": 560.2, "usd_sum": 0.000321 } }, { "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": 382, "output_tokens": 4, "latency_ms": 615.5, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 382, "output_tokens": 4, "latency_ms": 593.9, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 382, "output_tokens": 4, "latency_ms": 628.7, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 382.0, "output_tokens_mean": 4.0, "latency_ms_mean": 612.7, "usd_sum": 0.000312 } }, { "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": "4", "compliant": true, "score": 0.0, "detail": { "predicted": 4.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 378, "output_tokens": 4, "latency_ms": 632.5, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "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": 378, "output_tokens": 4, "latency_ms": 589.3, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "4", "compliant": true, "score": 0.0, "detail": { "predicted": 4.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 378, "output_tokens": 4, "latency_ms": 592.6, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "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": 378.0, "output_tokens_mean": 4.0, "latency_ms_mean": 604.8, "usd_sum": 0.000309 } }, { "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": 408, "output_tokens": 11, "latency_ms": 633.0, "usd": 0.000124, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "braised", "compliant": true, "score": 0.0, "detail": { "predicted": "braised", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 408, "output_tokens": 5, "latency_ms": 591.7, "usd": 0.000112, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "braised", "compliant": true, "score": 0.0, "detail": { "predicted": "braised", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 408, "output_tokens": 5, "latency_ms": 706.8, "usd": 0.000112, "model_version": "gpt-5.4-mini-2026-03-17", "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": 408.0, "output_tokens_mean": 7.0, "latency_ms_mean": 643.833, "usd_sum": 0.000348 } }, { "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": 354, "output_tokens": 8, "latency_ms": 536.6, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 354, "output_tokens": 8, "latency_ms": 589.2, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 354, "output_tokens": 8, "latency_ms": 750.3, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 354.0, "output_tokens_mean": 8.0, "latency_ms_mean": 625.367, "usd_sum": 0.000312 } }, { "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": "[\"starch\",\"main_protein\",\"sauce\",\"textural_element\",\"aromatic_garnish\",\"seasoning\"]", "compliant": true, "score": 0.7692, "detail": { "predicted": [ "aromatic_garnish", "main_protein", "sauce", "seasoning", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.8333, "recall": 0.7143 }, "metrics": { "input_tokens": 328, "output_tokens": 27, "latency_ms": 692.4, "usd": 0.000136, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"starch\",\"main_protein\",\"sauce\",\"main_vegetable\",\"textural_element\",\"seasoning\",\"aromatic_garnish\"]", "compliant": true, "score": 0.7143, "detail": { "predicted": [ "aromatic_garnish", "main_protein", "main_vegetable", "sauce", "seasoning", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.7143, "recall": 0.7143 }, "metrics": { "input_tokens": 328, "output_tokens": 32, "latency_ms": 726.9, "usd": 0.000146, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"starch\",\"main_protein\",\"sauce\",\"main_vegetable\",\"textural_element\",\"seasoning\",\"aromatic_garnish\"]", "compliant": true, "score": 0.7143, "detail": { "predicted": [ "aromatic_garnish", "main_protein", "main_vegetable", "sauce", "seasoning", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.7143, "recall": 0.7143 }, "metrics": { "input_tokens": 328, "output_tokens": 32, "latency_ms": 685.2, "usd": 0.000146, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7326, "score_summary": { "mean": 0.7326, "stdev": 0.0317, "sem": 0.0183, "ci95_lo": 0.6967, "ci95_hi": 0.7685, "n": 3 }, "score_if_valid": 0.7326, "format_rate": 1.0, "metrics": { "input_tokens_mean": 328.0, "output_tokens_mean": 30.333, "latency_ms_mean": 701.5, "usd_sum": 0.000428 } }, { "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": 308, "output_tokens": 4, "latency_ms": 627.7, "usd": 8.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 308, "output_tokens": 4, "latency_ms": 559.9, "usd": 8.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 308, "output_tokens": 4, "latency_ms": 591.8, "usd": 8.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 308.0, "output_tokens_mean": 4.0, "latency_ms_mean": 593.133, "usd_sum": 0.000255 } }, { "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": 413, "output_tokens": 5, "latency_ms": 655.2, "usd": 0.000113, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 413, "output_tokens": 5, "latency_ms": 702.7, "usd": 0.000113, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 413, "output_tokens": 5, "latency_ms": 602.2, "usd": 0.000113, "model_version": "gpt-5.4-mini-2026-03-17", "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": 413.0, "output_tokens_mean": 5.0, "latency_ms_mean": 653.367, "usd_sum": 0.000339 } }, { "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": 342, "output_tokens": 5, "latency_ms": 540.0, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 342, "output_tokens": 5, "latency_ms": 610.3, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 342, "output_tokens": 5, "latency_ms": 745.8, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 342.0, "output_tokens_mean": 5.0, "latency_ms_mean": 632.033, "usd_sum": 0.000288 } }, { "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": 313, "output_tokens": 4, "latency_ms": 507.0, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 750.1, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 607.1, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 621.4, "usd_sum": 0.000258 } }, { "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": 408, "output_tokens": 4, "latency_ms": 808.3, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 408, "output_tokens": 4, "latency_ms": 520.8, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 408, "output_tokens": 4, "latency_ms": 543.8, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 408.0, "output_tokens_mean": 4.0, "latency_ms_mean": 624.3, "usd_sum": 0.00033 } }, { "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": 910, "output_tokens": 4, "latency_ms": 420.2, "usd": 0.000236, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 910, "output_tokens": 4, "latency_ms": 750.1, "usd": 0.000236, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 910, "output_tokens": 4, "latency_ms": 630.0, "usd": 0.000236, "model_version": "gpt-5.4-mini-2026-03-17", "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": 910.0, "output_tokens_mean": 4.0, "latency_ms_mean": 600.1, "usd_sum": 0.000708 } }, { "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": 938, "output_tokens": 7, "latency_ms": 892.8, "usd": 0.000249, "model_version": "gpt-5.4-mini-2026-03-17", "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": 938, "output_tokens": 7, "latency_ms": 598.4, "usd": 0.000249, "model_version": "gpt-5.4-mini-2026-03-17", "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": 938, "output_tokens": 7, "latency_ms": 617.3, "usd": 0.000249, "model_version": "gpt-5.4-mini-2026-03-17", "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": 938.0, "output_tokens_mean": 7.0, "latency_ms_mean": 702.833, "usd_sum": 0.000747 } }, { "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": 890, "output_tokens": 4, "latency_ms": 606.0, "usd": 0.00023, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 890, "output_tokens": 4, "latency_ms": 606.0, "usd": 0.00023, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 890, "output_tokens": 4, "latency_ms": 642.1, "usd": 0.00023, "model_version": "gpt-5.4-mini-2026-03-17", "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": 890.0, "output_tokens_mean": 4.0, "latency_ms_mean": 618.033, "usd_sum": 0.00069 } }, { "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": "meat and dairy together", "compliant": true, "score": 0.0, "detail": { "predicted": "meat and dairy together", "expected": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "metrics": { "input_tokens": 884, "output_tokens": 8, "latency_ms": 615.6, "usd": 0.000237, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "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": 884, "output_tokens": 8, "latency_ms": 894.6, "usd": 0.000237, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "meat and dairy mixed", "compliant": true, "score": 1.0, "detail": { "predicted": "meat and dairy mixed", "expected": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "metrics": { "input_tokens": 884, "output_tokens": 8, "latency_ms": 570.2, "usd": 0.000237, "model_version": "gpt-5.4-mini-2026-03-17", "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": 884.0, "output_tokens_mean": 8.0, "latency_ms_mean": 693.467, "usd_sum": 0.000711 } }, { "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": "set:tree_nuts,milk", "compliant": true, "score": 0.5, "detail": { "predicted": [ "milk", "set:tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 933, "output_tokens": 10, "latency_ms": 632.3, "usd": 0.000253, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "set:tree_nuts,milk", "compliant": true, "score": 0.5, "detail": { "predicted": [ "milk", "set:tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 933, "output_tokens": 10, "latency_ms": 807.5, "usd": 0.000253, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "set:milk,tree_nuts", "compliant": true, "score": 0.5, "detail": { "predicted": [ "set:milk", "tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 933, "output_tokens": 10, "latency_ms": 652.5, "usd": 0.000253, "model_version": "gpt-5.4-mini-2026-03-17", "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": 933.0, "output_tokens_mean": 10.0, "latency_ms_mean": 697.433, "usd_sum": 0.000759 } }, { "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": "set:crustaceans,eggs,fish,peanuts", "compliant": true, "score": 0.75, "detail": { "predicted": [ "eggs", "fish", "peanuts", "set:crustaceans" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 887, "output_tokens": 17, "latency_ms": 474.6, "usd": 0.000256, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "set:crustaceans,eggs,fish,peanuts", "compliant": true, "score": 0.75, "detail": { "predicted": [ "eggs", "fish", "peanuts", "set:crustaceans" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 887, "output_tokens": 17, "latency_ms": 722.8, "usd": 0.000256, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "set:crustaceans,eggs,fish,peanuts", "compliant": true, "score": 0.75, "detail": { "predicted": [ "eggs", "fish", "peanuts", "set:crustaceans" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 887, "output_tokens": 17, "latency_ms": 571.5, "usd": 0.000256, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.75, "score_summary": { "mean": 0.75, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.75, "ci95_hi": 0.75, "n": 3 }, "score_if_valid": 0.75, "format_rate": 1.0, "metrics": { "input_tokens_mean": 887.0, "output_tokens_mean": 17.0, "latency_ms_mean": 589.633, "usd_sum": 0.000768 } }, { "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": 879, "output_tokens": 5, "latency_ms": 738.8, "usd": 0.00023, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "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": 879, "output_tokens": 5, "latency_ms": 646.2, "usd": 0.00023, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "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": 879, "output_tokens": 5, "latency_ms": 682.0, "usd": 0.00023, "model_version": "gpt-5.4-mini-2026-03-17", "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": 879.0, "output_tokens_mean": 5.0, "latency_ms_mean": 689.0, "usd_sum": 0.00069 } }, { "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": "riceflour", "compliant": true, "score": 0.0, "detail": { "predicted": "riceflour", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 866, "output_tokens": 6, "latency_ms": 510.9, "usd": 0.000228, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "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": 866, "output_tokens": 6, "latency_ms": 1614.5, "usd": 0.000228, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "riceflour", "compliant": true, "score": 0.0, "detail": { "predicted": "riceflour", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 866, "output_tokens": 6, "latency_ms": 520.6, "usd": 0.000228, "model_version": "gpt-5.4-mini-2026-03-17", "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": 866.0, "output_tokens_mean": 6.0, "latency_ms_mean": 882.0, "usd_sum": 0.000684 } }, { "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": "set:honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 0.8, "detail": { "predicted": [ "carmine", "set:honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 963, "output_tokens": 26, "latency_ms": 622.6, "usd": 0.000293, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "set:honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 0.8, "detail": { "predicted": [ "carmine", "set:honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 963, "output_tokens": 26, "latency_ms": 665.2, "usd": 0.000293, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "set:honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 0.8, "detail": { "predicted": [ "carmine", "set:honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 963, "output_tokens": 26, "latency_ms": 647.9, "usd": 0.000293, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.8, "score_summary": { "mean": 0.8, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.8, "ci95_hi": 0.8, "n": 3 }, "score_if_valid": 0.8, "format_rate": 1.0, "metrics": { "input_tokens_mean": 963.0, "output_tokens_mean": 26.0, "latency_ms_mean": 645.233, "usd_sum": 0.000879 } }, { "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": "set:cereals_containing_gluten,fish,molluscs", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "fish", "molluscs", "set:cereals_containing_gluten" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.6667, "recall": 0.6667 }, "metrics": { "input_tokens": 915, "output_tokens": 17, "latency_ms": 701.0, "usd": 0.000263, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "set:crustaceans,fish,cereals_containing_gluten,molluscs", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "cereals_containing_gluten", "fish", "molluscs", "set:crustaceans" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.75, "recall": 1.0 }, "metrics": { "input_tokens": 915, "output_tokens": 22, "latency_ms": 702.6, "usd": 0.000273, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "set:cereals_containing_gluten,fish,molluscs", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "fish", "molluscs", "set:cereals_containing_gluten" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.6667, "recall": 0.6667 }, "metrics": { "input_tokens": 915, "output_tokens": 17, "latency_ms": 526.9, "usd": 0.000263, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7302, "score_summary": { "mean": 0.7302, "stdev": 0.1099, "sem": 0.0635, "ci95_lo": 0.6058, "ci95_hi": 0.8546, "n": 3 }, "score_if_valid": 0.7302, "format_rate": 1.0, "metrics": { "input_tokens_mean": 915.0, "output_tokens_mean": 18.667, "latency_ms_mean": 643.5, "usd_sum": 0.000799 } }, { "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": "set:garlic-infused olive oil,white onion,wheat pasta,honey", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "honey", "set:garlic-infused olive oil", "wheat pasta", "white onion" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 0.75, "recall": 1.0 }, "metrics": { "input_tokens": 932, "output_tokens": 19, "latency_ms": 616.9, "usd": 0.000271, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "set:white onion,wheat pasta,honey", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "honey", "set:white onion", "wheat pasta" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 0.6667, "recall": 0.6667 }, "metrics": { "input_tokens": 932, "output_tokens": 11, "latency_ms": 547.6, "usd": 0.000255, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "set:white onion,wheat pasta,honey", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "honey", "set:white onion", "wheat pasta" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 0.6667, "recall": 0.6667 }, "metrics": { "input_tokens": 932, "output_tokens": 11, "latency_ms": 685.9, "usd": 0.000255, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7302, "score_summary": { "mean": 0.7302, "stdev": 0.1099, "sem": 0.0635, "ci95_lo": 0.6058, "ci95_hi": 0.8546, "n": 3 }, "score_if_valid": 0.7302, "format_rate": 1.0, "metrics": { "input_tokens_mean": 932.0, "output_tokens_mean": 13.667, "latency_ms_mean": 616.8, "usd_sum": 0.000781 } }, { "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": 892, "output_tokens": 7, "latency_ms": 1455.8, "usd": 0.000237, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "set:pescatarian", "compliant": true, "score": 0.0, "detail": { "predicted": [ "set:pescatarian" ], "expected": [ "pescatarian" ], "precision": 0.0, "recall": 0.0 }, "metrics": { "input_tokens": 892, "output_tokens": 8, "latency_ms": 636.0, "usd": 0.000239, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "set:pescatarian", "compliant": true, "score": 0.0, "detail": { "predicted": [ "set:pescatarian" ], "expected": [ "pescatarian" ], "precision": 0.0, "recall": 0.0 }, "metrics": { "input_tokens": 892, "output_tokens": 8, "latency_ms": 524.3, "usd": 0.000239, "model_version": "gpt-5.4-mini-2026-03-17", "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": 892.0, "output_tokens_mean": 7.667, "latency_ms_mean": 872.033, "usd_sum": 0.000715 } }, { "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": 498, "output_tokens": 4, "latency_ms": 529.4, "usd": 0.000132, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 498, "output_tokens": 4, "latency_ms": 558.5, "usd": 0.000132, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 498, "output_tokens": 4, "latency_ms": 600.4, "usd": 0.000132, "model_version": "gpt-5.4-mini-2026-03-17", "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": 498.0, "output_tokens_mean": 4.0, "latency_ms_mean": 562.767, "usd_sum": 0.000396 } }, { "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": 482, "output_tokens": 6, "latency_ms": 468.7, "usd": 0.000132, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 482, "output_tokens": 6, "latency_ms": 442.0, "usd": 0.000132, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 482, "output_tokens": 6, "latency_ms": 669.7, "usd": 0.000132, "model_version": "gpt-5.4-mini-2026-03-17", "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": 482.0, "output_tokens_mean": 6.0, "latency_ms_mean": 526.8, "usd_sum": 0.000396 } }, { "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": 479, "output_tokens": 5, "latency_ms": 603.5, "usd": 0.00013, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 479, "output_tokens": 5, "latency_ms": 641.3, "usd": 0.00013, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 479, "output_tokens": 5, "latency_ms": 490.8, "usd": 0.00013, "model_version": "gpt-5.4-mini-2026-03-17", "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": 479.0, "output_tokens_mean": 5.0, "latency_ms_mean": 578.533, "usd_sum": 0.00039 } }, { "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": 483, "output_tokens": 4, "latency_ms": 692.0, "usd": 0.000129, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 483, "output_tokens": 4, "latency_ms": 1281.0, "usd": 0.000129, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 483, "output_tokens": 4, "latency_ms": 549.3, "usd": 0.000129, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 840.767, "usd_sum": 0.000387 } }, { "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": 492, "output_tokens": 4, "latency_ms": 728.2, "usd": 0.000131, "model_version": "gpt-5.4-mini-2026-03-17", "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": 492, "output_tokens": 4, "latency_ms": 554.6, "usd": 0.000131, "model_version": "gpt-5.4-mini-2026-03-17", "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": 492, "output_tokens": 4, "latency_ms": 636.9, "usd": 0.000131, "model_version": "gpt-5.4-mini-2026-03-17", "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": 492.0, "output_tokens_mean": 4.0, "latency_ms_mean": 639.9, "usd_sum": 0.000393 } }, { "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": 496, "output_tokens": 6, "latency_ms": 1504.5, "usd": 0.000136, "model_version": "gpt-5.4-mini-2026-03-17", "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": 496, "output_tokens": 6, "latency_ms": 502.9, "usd": 0.000136, "model_version": "gpt-5.4-mini-2026-03-17", "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": 496, "output_tokens": 6, "latency_ms": 1020.7, "usd": 0.000136, "model_version": "gpt-5.4-mini-2026-03-17", "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": 496.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1009.367, "usd_sum": 0.000408 } }, { "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": 674, "output_tokens": 4, "latency_ms": 684.5, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 674, "output_tokens": 4, "latency_ms": 660.9, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 674, "output_tokens": 4, "latency_ms": 468.2, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "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": 674.0, "output_tokens_mean": 4.0, "latency_ms_mean": 604.533, "usd_sum": 0.000531 } }, { "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": 493, "output_tokens": 6, "latency_ms": 4836.2, "usd": 0.000135, "model_version": "gpt-5.4-mini-2026-03-17", "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": 493, "output_tokens": 12, "latency_ms": 632.5, "usd": 0.000147, "model_version": "gpt-5.4-mini-2026-03-17", "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": 493, "output_tokens": 6, "latency_ms": 1345.9, "usd": 0.000135, "model_version": "gpt-5.4-mini-2026-03-17", "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": 8.0, "latency_ms_mean": 2271.533, "usd_sum": 0.000417 } }, { "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": "The menu is over-committed to pumpkin/squash and purées, so the progression feels repetitive rather than layered. You move from pumpkin velouté to butternut squash risotto to pumpkin purée to sweet potato purée to pumpkin cheesecake, which creates structural monotony and blurs course identity. Autumnal is fine; this reads more like five variations on the same note.\n\nThere is also a clear allergen and dietary problem. The vegetarian path breaks at the fish and pork courses unless there is a defined alternate, and the nut-free path is undermined by amaretti crumble and pecan brittle. Brown butter and cheesecake also reduce flexibility, so the menu is not genuinely accommodating the stated constraints as written.\n\nOne constructive fix: replace the appetizer with a mushroom and chestnut arancini with cider emulsion, and swap the dessert to an apple tart with oat streusel, keeping the same seasonal mood. That gives stronger textural contrast, preserves the autumn theme, and creates a viable vegetarian and nut-free route without forcing the whole menu to rely on repeated squash purées or allergenic garnishes.", "compliant": true, "score": 0.88, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies multiple concrete weaknesses: repeated pumpkin/squash across the menu, purée/starch monotony, and nut/dietary-path problems." }, { "id": "remediation", "weight": 0.3, "score": 0.8, "note": "It proposes specific substitutions with named dishes and components, though chestnut introduces another nut issue and the fix does not fully resolve all stated constraints across all courses." }, { "id": "justification", "weight": 0.3, "score": 0.8, "note": "The reasoning is grounded in structural balance, course identity, texture contrast, and dietary viability, though it is lighter on explicit service-flow or food-cost mechanism." } ], "summary": "The answer follows the requested three-paragraph free-text format and avoids generic praise. It diagnoses the main menu flaws well and offers concrete seasonal changes, but the proposed chestnut component weakens the nut-free solution and the justification could be slightly more mechanistic.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1251, "output_tokens": 227, "latency_ms": 2327.0, "usd": 0.000767, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "The menu is structurally monotone: pumpkin, squash, sweet potato, cider, sage, spice, and brown butter repeat across every course, so the palate gets the same autumnal register five times. That reduces progression and makes the tasting feel flatter than it should, especially when the amuse and appetizer are both orange, sweet, and soft-textured. A stronger line-up would vary one or two courses toward sharp, bitter, or herb-driven notes to create contrast and reset the palate.\n\nThere is also a clear allergen and dietary problem. The current menu has no viable vegetarian path because the fish and pork courses anchor the progression, and the dessert is not nut-free because of pecan brittle; the appetizer also contains amaretti, which often brings almond into play. On top of that, brown butter and cheesecake add dairy-heavy exposure, so the menu is fragile for guests with common restrictions. Replacing the fish course with a roasted mushroom or celeriac dish would immediately improve the vegetarian option while preserving the autumn brief.\n\nOne specific constructive change: swap the pumpkin cheesecake with a spiced apple tart using oat crumble, and serve toasted seeds instead of pecans. That keeps the seasonal mood, lowers nut risk, and usually improves the cost-to-price ratio because apples and seeds are cheaper than cheesecake components and nuts, helping the dessert better fit a 30% food-cost target. It would also make the final course feel lighter and less repetitive, ending the menu with a cleaner finish rather than another dense, creamy pumpkin variation.", "compliant": true, "score": 0.91, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies multiple concrete weaknesses: repeated pumpkin/squash-autumn flavor monotony, soft/starchy structural heaviness, and nut/dietary-path problems from amaretti and pecans." }, { "id": "remediation", "weight": 0.3, "score": 0.8, "note": "It proposes a specific seasonal swap to apple tart with oat crumble and seeds that directly addresses repetition, nut risk, and cost, though it leaves the vegetarian path only partially solved." }, { "id": "justification", "weight": 0.3, "score": 0.9, "note": "The reasoning is mechanism-based, citing palate progression, texture contrast, allergen exposure, and food-cost impact rather than generic praise." } ], "summary": "The answer follows the required three-paragraph free-text format and gives a focused critique without generic praise. It diagnoses several defensible menu flaws and offers a concrete seasonal fix with solid operational justification, though its vegetarian remediation is less fully developed than its dessert change.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1251, "output_tokens": 308, "latency_ms": 2694.7, "usd": 0.000929, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "The menu is structurally monotone: pumpkin/butternut/sweet potato dominate every course, so the palate keeps getting the same sweet, orange, dense profile. That reduces contrast and makes the progression feel flatter than a true tasting menu, especially because there is very little sharp acid, bitterness, or herbaceous lift to reset the palate between courses.\n\nIt also has clear allergen and dietary risk. The vegetarian path breaks at the fish and pork courses, and the nut-free path is not viable because the appetizer uses amaretti crumble and the dessert uses pecan brittle; brown butter also rules out dairy-free, though that was not requested. In addition, the menu stacks richer items one after another, so the middle and end may feel heavy rather than balanced.\n\nA specific fix: replace the fish course with a mushroom or celeriac-based course, and remove the nut garnishes by swapping the amaretti crumble for toasted breadcrumb or seed crumble and the pecan brittle for oat streusel. That single adjustment creates a real vegetarian and nut-free route, while also improving flow by introducing more textural contrast and giving you better control over food cost if scallops and pecans are driving the price above the 30% target.", "compliant": true, "score": 0.91, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies multiple concrete weaknesses: repeated pumpkin/sweet-starch monotony, nut-allergen blockage, and heavy consecutive rich textures." }, { "id": "remediation", "weight": 0.3, "score": 0.8, "note": "It proposes actionable substitutions for the fish course and nut components, though the replacement course is somewhat broad rather than a fully specified dish." }, { "id": "justification", "weight": 0.3, "score": 0.9, "note": "The reasoning is mechanism-based, citing palate reset, textural contrast, dietary-path viability, and food-cost pressure rather than generic praise." } ], "summary": "The candidate directly critiques the menu with specific, defensible weaknesses and avoids generic praise. Its proposed fix is practical and tied to flow, allergen management, and cost, though the replacement course could be more precisely defined.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1251, "output_tokens": 249, "latency_ms": 2174.3, "usd": 0.000811, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.9, "score_summary": { "mean": 0.9, "stdev": 0.0173, "sem": 0.01, "ci95_lo": 0.8804, "ci95_hi": 0.9196, "n": 3 }, "score_if_valid": 0.9, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1251.0, "output_tokens_mean": 261.333, "latency_ms_mean": 2398.667, "usd_sum": 0.002507 } }, { "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": 342, "output_tokens": 5, "latency_ms": 659.9, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 342, "output_tokens": 5, "latency_ms": 746.1, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 342, "output_tokens": 5, "latency_ms": 627.4, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 342.0, "output_tokens_mean": 5.0, "latency_ms_mean": 677.8, "usd_sum": 0.000288 } }, { "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": 259, "output_tokens": 6, "latency_ms": 763.1, "usd": 7.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 259, "output_tokens": 6, "latency_ms": 659.4, "usd": 7.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 259, "output_tokens": 12, "latency_ms": 816.1, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 259.0, "output_tokens_mean": 8.0, "latency_ms_mean": 746.2, "usd_sum": 0.000243 } }, { "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": 263, "output_tokens": 5, "latency_ms": 552.7, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 263, "output_tokens": 5, "latency_ms": 772.3, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 263, "output_tokens": 5, "latency_ms": 721.3, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 682.1, "usd_sum": 0.000228 } }, { "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": 396, "output_tokens": 5, "latency_ms": 889.9, "usd": 0.000109, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 396, "output_tokens": 5, "latency_ms": 1899.9, "usd": 0.000109, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 396, "output_tokens": 5, "latency_ms": 779.8, "usd": 0.000109, "model_version": "gpt-5.4-mini-2026-03-17", "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": 396.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1189.867, "usd_sum": 0.000327 } }, { "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": 263, "output_tokens": 5, "latency_ms": 606.7, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 263, "output_tokens": 5, "latency_ms": 766.9, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 263, "output_tokens": 5, "latency_ms": 3492.2, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 1621.933, "usd_sum": 0.000228 } }, { "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": "[2,7,6,0,2]", "compliant": true, "score": 0.2, "detail": { "per_position": [ { "index": 0, "predicted": 2, "expected": 1, "score": 0.3333 }, { "index": 1, "predicted": 7, "expected": 5, "score": 0.0 }, { "index": 2, "predicted": 6, "expected": 4, "score": 0.0 }, { "index": 3, "predicted": 0, "expected": 1, "score": 0.3333 }, { "index": 4, "predicted": 2, "expected": 3, "score": 0.3333 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 372, "output_tokens": 14, "latency_ms": 755.7, "usd": 0.000121, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[2, 5.5, 4, 0.5, 1]", "compliant": true, "score": 0.5333, "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": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 1, "expected": 3, "score": 0.0 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 372, "output_tokens": 22, "latency_ms": 812.6, "usd": 0.000137, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[2,7,4,0,2]", "compliant": true, "score": 0.4, "detail": { "per_position": [ { "index": 0, "predicted": 2, "expected": 1, "score": 0.3333 }, { "index": 1, "predicted": 7, "expected": 5, "score": 0.0 }, { "index": 2, "predicted": 4, "expected": 4, "score": 1.0 }, { "index": 3, "predicted": 0, "expected": 1, "score": 0.3333 }, { "index": 4, "predicted": 2, "expected": 3, "score": 0.3333 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 372, "output_tokens": 14, "latency_ms": 557.9, "usd": 0.000121, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.3778, "score_summary": { "mean": 0.3778, "stdev": 0.1678, "sem": 0.0969, "ci95_lo": 0.1879, "ci95_hi": 0.5676, "n": 3 }, "score_if_valid": 0.3778, "format_rate": 1.0, "metrics": { "input_tokens_mean": 372.0, "output_tokens_mean": 16.667, "latency_ms_mean": 708.733, "usd_sum": 0.000379 } }, { "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": 265, "output_tokens": 12, "latency_ms": 566.1, "usd": 9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 265, "output_tokens": 6, "latency_ms": 724.7, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 265, "output_tokens": 6, "latency_ms": 1021.9, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 265.0, "output_tokens_mean": 8.0, "latency_ms_mean": 770.9, "usd_sum": 0.000246 } }, { "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": 328, "output_tokens": 5, "latency_ms": 632.5, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 328, "output_tokens": 5, "latency_ms": 1046.4, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 328, "output_tokens": 5, "latency_ms": 543.4, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 328.0, "output_tokens_mean": 5.0, "latency_ms_mean": 740.767, "usd_sum": 0.000276 } }, { "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": 332, "output_tokens": 4, "latency_ms": 766.8, "usd": 9.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 4, "latency_ms": 653.0, "usd": 9.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 4, "latency_ms": 506.8, "usd": 9.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 642.2, "usd_sum": 0.000273 } }, { "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": 338, "output_tokens": 5, "latency_ms": 719.5, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 338, "output_tokens": 5, "latency_ms": 1223.2, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 338, "output_tokens": 5, "latency_ms": 609.6, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 338.0, "output_tokens_mean": 5.0, "latency_ms_mean": 850.767, "usd_sum": 0.000282 } }, { "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": "355", "compliant": true, "score": 0.0, "detail": { "predicted": 355.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 815, "output_tokens": 4, "latency_ms": 476.8, "usd": 0.000212, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "355", "compliant": true, "score": 0.0, "detail": { "predicted": 355.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 815, "output_tokens": 4, "latency_ms": 644.8, "usd": 0.000212, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "375", "compliant": true, "score": 1.0, "detail": { "predicted": 375.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 815, "output_tokens": 4, "latency_ms": 511.8, "usd": 0.000212, "model_version": "gpt-5.4-mini-2026-03-17", "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": 815.0, "output_tokens_mean": 4.0, "latency_ms_mean": 544.467, "usd_sum": 0.000636 } }, { "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": "118", "compliant": true, "score": 0.2, "detail": { "predicted": 118.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 824, "output_tokens": 4, "latency_ms": 725.9, "usd": 0.000214, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "82", "compliant": true, "score": 0.0, "detail": { "predicted": 82.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 824, "output_tokens": 4, "latency_ms": 611.0, "usd": 0.000214, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "86", "compliant": true, "score": 0.0, "detail": { "predicted": 86.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 824, "output_tokens": 4, "latency_ms": 851.4, "usd": 0.000214, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.0667, "score_summary": { "mean": 0.0667, "stdev": 0.1155, "sem": 0.0667, "ci95_lo": -0.064, "ci95_hi": 0.1973, "n": 3 }, "score_if_valid": 0.0667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 824.0, "output_tokens_mean": 4.0, "latency_ms_mean": 729.433, "usd_sum": 0.000642 } }, { "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": "650", "compliant": true, "score": 0.0, "detail": { "predicted": 650.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 825, "output_tokens": 10, "latency_ms": 500.7, "usd": 0.000226, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "674", "compliant": true, "score": 0.6, "detail": { "predicted": 674.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 825, "output_tokens": 4, "latency_ms": 560.6, "usd": 0.000214, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "656", "compliant": true, "score": 0.2, "detail": { "predicted": 656.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 825, "output_tokens": 10, "latency_ms": 798.2, "usd": 0.000226, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.2667, "score_summary": { "mean": 0.2667, "stdev": 0.3055, "sem": 0.1764, "ci95_lo": -0.079, "ci95_hi": 0.6124, "n": 3 }, "score_if_valid": 0.2667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 825.0, "output_tokens_mean": 8.0, "latency_ms_mean": 619.833, "usd_sum": 0.000666 } }, { "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": "66", "compliant": true, "score": 0.0, "detail": { "predicted": 66.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 811, "output_tokens": 10, "latency_ms": 675.6, "usd": 0.000223, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "36", "compliant": true, "score": 0.0, "detail": { "predicted": 36.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 811, "output_tokens": 10, "latency_ms": 669.6, "usd": 0.000223, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "33", "compliant": true, "score": 0.0, "detail": { "predicted": 33.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 811, "output_tokens": 4, "latency_ms": 665.1, "usd": 0.000211, "model_version": "gpt-5.4-mini-2026-03-17", "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": 811.0, "output_tokens_mean": 8.0, "latency_ms_mean": 670.1, "usd_sum": 0.000657 } }, { "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": "[66.38, 15.955, 8.415, 399]", "compliant": true, "score": 0.2979, "detail": { "per_position": [ { "index": 0, "predicted": 66.38, "expected": 64.3, "score": 0.3067 }, { "index": 1, "predicted": 15.955, "expected": 16.3, "score": 0.885 }, { "index": 2, "predicted": 8.415, "expected": 13.7, "score": 0.0 }, { "index": 3, "predicted": 399, "expected": 446, "score": 0.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 889, "output_tokens": 21, "latency_ms": 699.6, "usd": 0.000264, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[66.19, 12.8, 15.9, 459]", "compliant": true, "score": 0.1592, "detail": { "per_position": [ { "index": 0, "predicted": 66.19, "expected": 64.3, "score": 0.37 }, { "index": 1, "predicted": 12.8, "expected": 16.3, "score": 0.0 }, { "index": 2, "predicted": 15.9, "expected": 13.7, "score": 0.2667 }, { "index": 3, "predicted": 459, "expected": 446, "score": 0.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 889, "output_tokens": 21, "latency_ms": 719.7, "usd": 0.000264, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[65.48, 15.55, 8.775, 374]", "compliant": true, "score": 0.3392, "detail": { "per_position": [ { "index": 0, "predicted": 65.48, "expected": 64.3, "score": 0.6067 }, { "index": 1, "predicted": 15.55, "expected": 16.3, "score": 0.75 }, { "index": 2, "predicted": 8.775, "expected": 13.7, "score": 0.0 }, { "index": 3, "predicted": 374, "expected": 446, "score": 0.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 889, "output_tokens": 21, "latency_ms": 660.7, "usd": 0.000264, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.2654, "score_summary": { "mean": 0.2654, "stdev": 0.0943, "sem": 0.0544, "ci95_lo": 0.1587, "ci95_hi": 0.3721, "n": 3 }, "score_if_valid": 0.2654, "format_rate": 1.0, "metrics": { "input_tokens_mean": 889.0, "output_tokens_mean": 21.0, "latency_ms_mean": 693.333, "usd_sum": 0.000792 } }, { "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": "53", "compliant": true, "score": 0.0, "detail": { "predicted": 53.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 808, "output_tokens": 10, "latency_ms": 754.4, "usd": 0.000222, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "92", "compliant": true, "score": 0.0, "detail": { "predicted": 92.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 808, "output_tokens": 10, "latency_ms": 619.0, "usd": 0.000222, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "94", "compliant": true, "score": 0.0, "detail": { "predicted": 94.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 808, "output_tokens": 10, "latency_ms": 673.4, "usd": 0.000222, "model_version": "gpt-5.4-mini-2026-03-17", "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": 808.0, "output_tokens_mean": 10.0, "latency_ms_mean": 682.267, "usd_sum": 0.000666 } }, { "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", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.1 }, "metrics": { "input_tokens": 772, "output_tokens": 4, "latency_ms": 817.7, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "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": 772, "output_tokens": 4, "latency_ms": 547.0, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.1 }, "metrics": { "input_tokens": 772, "output_tokens": 4, "latency_ms": 623.1, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "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": 772.0, "output_tokens_mean": 4.0, "latency_ms_mean": 662.6, "usd_sum": 0.000603 } }, { "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": 786, "output_tokens": 5, "latency_ms": 707.9, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "1046", "compliant": true, "score": 1.0, "detail": { "predicted": 1046.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 786, "output_tokens": 5, "latency_ms": 457.6, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "1046", "compliant": true, "score": 1.0, "detail": { "predicted": 1046.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 786, "output_tokens": 5, "latency_ms": 618.0, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "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": 786.0, "output_tokens_mean": 5.0, "latency_ms_mean": 594.5, "usd_sum": 0.000621 } }, { "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": "[1.372, 5.162, 35.08, 349]", "compliant": true, "score": 0.1795, "detail": { "per_position": [ { "index": 0, "predicted": 1.372, "expected": 2.5, "score": 0.718 }, { "index": 1, "predicted": 5.162, "expected": 9.6, "score": 0.0 }, { "index": 2, "predicted": 35.08, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 349, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 894, "output_tokens": 21, "latency_ms": 2510.8, "usd": 0.000266, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[1.272,8.32,50.84,487]", "compliant": true, "score": 0.3433, "detail": { "per_position": [ { "index": 0, "predicted": 1.272, "expected": 2.5, "score": 0.693 }, { "index": 1, "predicted": 8.32, "expected": 9.6, "score": 0.68 }, { "index": 2, "predicted": 50.84, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 487, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 894, "output_tokens": 18, "latency_ms": 1048.8, "usd": 0.00026, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[1.124, 5.264, 66.4, 624]", "compliant": true, "score": 0.164, "detail": { "per_position": [ { "index": 0, "predicted": 1.124, "expected": 2.5, "score": 0.656 }, { "index": 1, "predicted": 5.264, "expected": 9.6, "score": 0.0 }, { "index": 2, "predicted": 66.4, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 624, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 894, "output_tokens": 21, "latency_ms": 686.3, "usd": 0.000266, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.2289, "score_summary": { "mean": 0.2289, "stdev": 0.0993, "sem": 0.0574, "ci95_lo": 0.1165, "ci95_hi": 0.3414, "n": 3 }, "score_if_valid": 0.2289, "format_rate": 1.0, "metrics": { "input_tokens_mean": 894.0, "output_tokens_mean": 20.0, "latency_ms_mean": 1415.3, "usd_sum": 0.000792 } }, { "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": 812, "output_tokens": 5, "latency_ms": 547.1, "usd": 0.000213, "model_version": "gpt-5.4-mini-2026-03-17", "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": 812, "output_tokens": 5, "latency_ms": 1020.6, "usd": 0.000213, "model_version": "gpt-5.4-mini-2026-03-17", "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": 812, "output_tokens": 5, "latency_ms": 618.4, "usd": 0.000213, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 728.7, "usd_sum": 0.000639 } }, { "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": 377, "output_tokens": 4, "latency_ms": 634.2, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 377, "output_tokens": 4, "latency_ms": 556.3, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 377, "output_tokens": 4, "latency_ms": 467.7, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "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": 377.0, "output_tokens_mean": 4.0, "latency_ms_mean": 552.733, "usd_sum": 0.000306 } }, { "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": 364, "output_tokens": 4, "latency_ms": 568.9, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 364, "output_tokens": 4, "latency_ms": 723.5, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 364, "output_tokens": 4, "latency_ms": 546.0, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 364.0, "output_tokens_mean": 4.0, "latency_ms_mean": 612.8, "usd_sum": 0.000297 } }, { "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": 377, "output_tokens": 10, "latency_ms": 503.8, "usd": 0.000114, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 377, "output_tokens": 10, "latency_ms": 541.5, "usd": 0.000114, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 377, "output_tokens": 10, "latency_ms": 644.4, "usd": 0.000114, "model_version": "gpt-5.4-mini-2026-03-17", "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": 377.0, "output_tokens_mean": 10.0, "latency_ms_mean": 563.233, "usd_sum": 0.000342 } }, { "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": 348, "output_tokens": 10, "latency_ms": 642.1, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 348, "output_tokens": 4, "latency_ms": 612.6, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 348, "output_tokens": 4, "latency_ms": 701.4, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 348.0, "output_tokens_mean": 6.0, "latency_ms_mean": 652.033, "usd_sum": 0.000297 } }, { "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": 351, "output_tokens": 4, "latency_ms": 627.8, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 351, "output_tokens": 4, "latency_ms": 599.9, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 351, "output_tokens": 4, "latency_ms": 411.4, "usd": 9.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 546.367, "usd_sum": 0.000288 } }, { "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": 369, "output_tokens": 4, "latency_ms": 531.3, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 369, "output_tokens": 4, "latency_ms": 573.9, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 369, "output_tokens": 4, "latency_ms": 602.1, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "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": 369.0, "output_tokens_mean": 4.0, "latency_ms_mean": 569.1, "usd_sum": 0.0003 } }, { "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": "d", "compliant": true, "score": 0.1, "detail": { "predicted": "d", "expected_best": "a", "rank": 2 }, "metrics": { "input_tokens": 370, "output_tokens": 4, "latency_ms": 504.8, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 560.9, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 487.4, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7, "score_summary": { "mean": 0.7, "stdev": 0.5196, "sem": 0.3, "ci95_lo": 0.112, "ci95_hi": 1.288, "n": 3 }, "score_if_valid": 0.7, "format_rate": 1.0, "metrics": { "input_tokens_mean": 370.0, "output_tokens_mean": 4.0, "latency_ms_mean": 517.7, "usd_sum": 0.000303 } }, { "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": 383, "output_tokens": 4, "latency_ms": 583.9, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 383, "output_tokens": 4, "latency_ms": 562.7, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 383, "output_tokens": 4, "latency_ms": 569.2, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 383.0, "output_tokens_mean": 4.0, "latency_ms_mean": 571.933, "usd_sum": 0.000312 } }, { "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": 370, "output_tokens": 4, "latency_ms": 635.1, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 786.5, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 415.8, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 612.467, "usd_sum": 0.000303 } }, { "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": 349, "output_tokens": 4, "latency_ms": 624.3, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 443.7, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 10, "latency_ms": 791.5, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 6.0, "latency_ms_mean": 619.833, "usd_sum": 0.000297 } }, { "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": 345, "output_tokens": 4, "latency_ms": 625.9, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 603.7, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 499.8, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 576.467, "usd_sum": 0.000282 } }, { "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": 360, "output_tokens": 4, "latency_ms": 641.0, "usd": 9.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 360, "output_tokens": 4, "latency_ms": 623.8, "usd": 9.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "c", "compliant": true, "score": 0.15, "detail": { "predicted": "c", "expected_best": "a", "rank": 1 }, "metrics": { "input_tokens": 360, "output_tokens": 4, "latency_ms": 537.1, "usd": 9.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7167, "score_summary": { "mean": 0.7167, "stdev": 0.4907, "sem": 0.2833, "ci95_lo": 0.1613, "ci95_hi": 1.272, "n": 3 }, "score_if_valid": 0.7167, "format_rate": 1.0, "metrics": { "input_tokens_mean": 360.0, "output_tokens_mean": 4.0, "latency_ms_mean": 600.633, "usd_sum": 0.000294 } }, { "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": 346, "output_tokens": 4, "latency_ms": 651.2, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 596.3, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 758.8, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 668.767, "usd_sum": 0.000285 } }, { "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": 345, "output_tokens": 4, "latency_ms": 770.9, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 488.0, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 526.4, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 595.1, "usd_sum": 0.000282 } }, { "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": 346, "output_tokens": 4, "latency_ms": 496.9, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 524.8, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 595.2, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 538.967, "usd_sum": 0.000285 } }, { "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": 365, "output_tokens": 4, "latency_ms": 603.7, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 365, "output_tokens": 4, "latency_ms": 647.1, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 365, "output_tokens": 4, "latency_ms": 639.9, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 630.233, "usd_sum": 0.000297 } }, { "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": 348, "output_tokens": 4, "latency_ms": 589.8, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 348, "output_tokens": 4, "latency_ms": 901.8, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 348, "output_tokens": 4, "latency_ms": 592.4, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 348.0, "output_tokens_mean": 4.0, "latency_ms_mean": 694.667, "usd_sum": 0.000285 } }, { "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": 349, "output_tokens": 4, "latency_ms": 624.4, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 660.5, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 466.1, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 583.667, "usd_sum": 0.000285 } }, { "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": 344, "output_tokens": 4, "latency_ms": 672.7, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 344, "output_tokens": 4, "latency_ms": 774.9, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 344, "output_tokens": 4, "latency_ms": 627.4, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 344.0, "output_tokens_mean": 4.0, "latency_ms_mean": 691.667, "usd_sum": 0.000282 } }, { "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": 370, "output_tokens": 5, "latency_ms": 634.9, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 370, "output_tokens": 5, "latency_ms": 750.1, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 370, "output_tokens": 5, "latency_ms": 539.6, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 641.533, "usd_sum": 0.000306 } }, { "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": 245, "output_tokens": 6, "latency_ms": 589.7, "usd": 7.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 245, "output_tokens": 6, "latency_ms": 688.9, "usd": 7.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 245, "output_tokens": 6, "latency_ms": 767.2, "usd": 7.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 245.0, "output_tokens_mean": 6.0, "latency_ms_mean": 681.933, "usd_sum": 0.000219 } }, { "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": 245, "output_tokens": 5, "latency_ms": 532.4, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 245, "output_tokens": 5, "latency_ms": 536.6, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 245, "output_tokens": 5, "latency_ms": 629.0, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 245.0, "output_tokens_mean": 5.0, "latency_ms_mean": 566.0, "usd_sum": 0.000213 } }, { "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": 240, "output_tokens": 4, "latency_ms": 501.8, "usd": 6.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 240, "output_tokens": 4, "latency_ms": 861.7, "usd": 6.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 240, "output_tokens": 4, "latency_ms": 612.7, "usd": 6.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 240.0, "output_tokens_mean": 4.0, "latency_ms_mean": 658.733, "usd_sum": 0.000204 } }, { "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": 250, "output_tokens": 7, "latency_ms": 556.1, "usd": 7.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Gewurztraminer", "compliant": true, "score": 1.0, "detail": { "predicted": "gewurztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 250, "output_tokens": 7, "latency_ms": 513.0, "usd": 7.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Gewürztraminer", "compliant": true, "score": 0.0, "detail": { "predicted": "gewürztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 250, "output_tokens": 8, "latency_ms": 858.6, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 250.0, "output_tokens_mean": 7.333, "latency_ms_mean": 642.567, "usd_sum": 0.000232 } }, { "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": 256, "output_tokens": 6, "latency_ms": 598.5, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 6, "latency_ms": 671.0, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 6, "latency_ms": 614.8, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 6.0, "latency_ms_mean": 628.1, "usd_sum": 0.000228 } }, { "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": "crianza", "compliant": true, "score": 0.0, "detail": { "predicted": "crianza", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 294, "output_tokens": 5, "latency_ms": 733.8, "usd": 8.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 294, "output_tokens": 4, "latency_ms": 618.5, "usd": 8.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "crianza", "compliant": true, "score": 0.0, "detail": { "predicted": "crianza", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 294, "output_tokens": 5, "latency_ms": 660.9, "usd": 8.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 294.0, "output_tokens_mean": 4.667, "latency_ms_mean": 671.067, "usd_sum": 0.000248 } }, { "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": "South Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "south korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 255, "output_tokens": 5, "latency_ms": 629.7, "usd": 7.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "South Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "south korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 255, "output_tokens": 5, "latency_ms": 699.7, "usd": 7.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "South Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "south korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 255, "output_tokens": 5, "latency_ms": 631.5, "usd": 7.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 255.0, "output_tokens_mean": 5.0, "latency_ms_mean": 653.633, "usd_sum": 0.000222 } }, { "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": 255, "output_tokens": 6, "latency_ms": 804.6, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 255, "output_tokens": 6, "latency_ms": 580.6, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 255, "output_tokens": 6, "latency_ms": 729.1, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 255.0, "output_tokens_mean": 6.0, "latency_ms_mean": 704.767, "usd_sum": 0.000228 } }, { "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": 255, "output_tokens": 5, "latency_ms": 655.4, "usd": 7.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 255, "output_tokens": 11, "latency_ms": 779.9, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 255, "output_tokens": 11, "latency_ms": 889.5, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 255.0, "output_tokens_mean": 9.0, "latency_ms_mean": 774.933, "usd_sum": 0.000246 } }, { "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": 256, "output_tokens": 4, "latency_ms": 432.5, "usd": 7.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 4, "latency_ms": 703.9, "usd": 7.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 4, "latency_ms": 578.6, "usd": 7.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 571.667, "usd_sum": 0.000216 } }, { "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": 262, "output_tokens": 6, "latency_ms": 783.9, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Muscadet", "compliant": true, "score": 1.0, "detail": { "predicted": "muscadet", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 262, "output_tokens": 6, "latency_ms": 618.5, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Muscadet", "compliant": true, "score": 1.0, "detail": { "predicted": "muscadet", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 262, "output_tokens": 6, "latency_ms": 1077.0, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 6.0, "latency_ms_mean": 826.467, "usd_sum": 0.000234 } }, { "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": 267, "output_tokens": 7, "latency_ms": 638.0, "usd": 8.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 267, "output_tokens": 7, "latency_ms": 689.5, "usd": 8.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 267, "output_tokens": 7, "latency_ms": 1288.6, "usd": 8.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 267.0, "output_tokens_mean": 7.0, "latency_ms_mean": 872.033, "usd_sum": 0.000243 } }, { "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": 251, "output_tokens": 4, "latency_ms": 607.4, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 251, "output_tokens": 4, "latency_ms": 473.3, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 251, "output_tokens": 4, "latency_ms": 610.2, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 563.633, "usd_sum": 0.000213 } }, { "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": 259, "output_tokens": 5, "latency_ms": 794.3, "usd": 7.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 259, "output_tokens": 5, "latency_ms": 609.0, "usd": 7.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 259, "output_tokens": 5, "latency_ms": 609.4, "usd": 7.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 259.0, "output_tokens_mean": 5.0, "latency_ms_mean": 670.9, "usd_sum": 0.000225 } }, { "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 Blanc", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon blanc", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 256, "output_tokens": 7, "latency_ms": 756.4, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 256, "output_tokens": 7, "latency_ms": 566.4, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 256, "output_tokens": 7, "latency_ms": 582.2, "usd": 7.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 7.0, "latency_ms_mean": 635.0, "usd_sum": 0.000234 } }, { "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": 249, "output_tokens": 4, "latency_ms": 833.7, "usd": 7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 249, "output_tokens": 4, "latency_ms": 584.4, "usd": 7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 249, "output_tokens": 4, "latency_ms": 490.4, "usd": 7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 249.0, "output_tokens_mean": 4.0, "latency_ms_mean": 636.167, "usd_sum": 0.00021 } }, { "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": 256, "output_tokens": 5, "latency_ms": 730.3, "usd": 7.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 5, "latency_ms": 507.7, "usd": 7.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 256, "output_tokens": 6, "latency_ms": 597.0, "usd": 7.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.333, "latency_ms_mean": 611.667, "usd_sum": 0.000224 } }, { "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": 252, "output_tokens": 4, "latency_ms": 385.6, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 252, "output_tokens": 4, "latency_ms": 650.5, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 252, "output_tokens": 4, "latency_ms": 598.6, "usd": 7.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 544.9, "usd_sum": 0.000213 } }, { "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": 261, "output_tokens": 5, "latency_ms": 518.1, "usd": 7.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 261, "output_tokens": 5, "latency_ms": 684.5, "usd": 7.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 261, "output_tokens": 5, "latency_ms": 725.9, "usd": 7.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 261.0, "output_tokens_mean": 5.0, "latency_ms_mean": 642.833, "usd_sum": 0.000225 } }, { "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": 277, "output_tokens": 6, "latency_ms": 528.2, "usd": 8.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 277, "output_tokens": 6, "latency_ms": 564.5, "usd": 8.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "Godello", "compliant": true, "score": 0.0, "detail": { "predicted": "godello", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 277, "output_tokens": 5, "latency_ms": 593.6, "usd": 7.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 277.0, "output_tokens_mean": 5.667, "latency_ms_mean": 562.1, "usd_sum": 0.000241 } }, { "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": 636, "output_tokens": 10, "latency_ms": 615.7, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 636, "output_tokens": 10, "latency_ms": 593.6, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 636, "output_tokens": 10, "latency_ms": 601.7, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 636.0, "output_tokens_mean": 10.0, "latency_ms_mean": 603.667, "usd_sum": 0.000537 } }, { "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": 638, "output_tokens": 10, "latency_ms": 645.7, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 638, "output_tokens": 10, "latency_ms": 640.0, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 638, "output_tokens": 10, "latency_ms": 581.0, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 10.0, "latency_ms_mean": 622.233, "usd_sum": 0.000537 } }, { "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": 641, "output_tokens": 9, "latency_ms": 648.4, "usd": 0.000178, "model_version": "gpt-5.4-mini-2026-03-17", "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": 641, "output_tokens": 9, "latency_ms": 647.2, "usd": 0.000178, "model_version": "gpt-5.4-mini-2026-03-17", "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": 641, "output_tokens": 9, "latency_ms": 587.0, "usd": 0.000178, "model_version": "gpt-5.4-mini-2026-03-17", "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": 9.0, "latency_ms_mean": 627.533, "usd_sum": 0.000534 } }, { "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": 603, "output_tokens": 4, "latency_ms": 612.4, "usd": 0.000159, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 603, "output_tokens": 10, "latency_ms": 697.1, "usd": 0.000171, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 603, "output_tokens": 4, "latency_ms": 555.5, "usd": 0.000159, "model_version": "gpt-5.4-mini-2026-03-17", "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": 603.0, "output_tokens_mean": 6.0, "latency_ms_mean": 621.667, "usd_sum": 0.000489 } }, { "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": 630, "output_tokens": 11, "latency_ms": 650.3, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 630, "output_tokens": 11, "latency_ms": 652.4, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 630, "output_tokens": 11, "latency_ms": 705.0, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 630.0, "output_tokens_mean": 11.0, "latency_ms_mean": 669.233, "usd_sum": 0.000537 } }, { "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": 636, "output_tokens": 10, "latency_ms": 609.9, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 636, "output_tokens": 10, "latency_ms": 623.9, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 636, "output_tokens": 10, "latency_ms": 612.9, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 636.0, "output_tokens_mean": 10.0, "latency_ms_mean": 615.567, "usd_sum": 0.000537 } }, { "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": 639, "output_tokens": 16, "latency_ms": 625.0, "usd": 0.000192, "model_version": "gpt-5.4-mini-2026-03-17", "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": 16, "latency_ms": 651.6, "usd": 0.000192, "model_version": "gpt-5.4-mini-2026-03-17", "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": 10, "latency_ms": 652.3, "usd": 0.00018, "model_version": "gpt-5.4-mini-2026-03-17", "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": 14.0, "latency_ms_mean": 642.967, "usd_sum": 0.000564 } }, { "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": 641, "output_tokens": 10, "latency_ms": 659.1, "usd": 0.00018, "model_version": "gpt-5.4-mini-2026-03-17", "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": 641, "output_tokens": 10, "latency_ms": 764.1, "usd": 0.00018, "model_version": "gpt-5.4-mini-2026-03-17", "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": 641, "output_tokens": 10, "latency_ms": 621.0, "usd": 0.00018, "model_version": "gpt-5.4-mini-2026-03-17", "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": 10.0, "latency_ms_mean": 681.4, "usd_sum": 0.00054 } }, { "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": 637, "output_tokens": 9, "latency_ms": 639.7, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "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": 637, "output_tokens": 9, "latency_ms": 623.9, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "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": 637, "output_tokens": 9, "latency_ms": 550.9, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "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": 9.0, "latency_ms_mean": 604.833, "usd_sum": 0.000531 } }, { "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": 633, "output_tokens": 11, "latency_ms": 804.7, "usd": 0.00018, "model_version": "gpt-5.4-mini-2026-03-17", "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": 633, "output_tokens": 11, "latency_ms": 516.6, "usd": 0.00018, "model_version": "gpt-5.4-mini-2026-03-17", "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": 633, "output_tokens": 11, "latency_ms": 669.5, "usd": 0.00018, "model_version": "gpt-5.4-mini-2026-03-17", "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": 633.0, "output_tokens_mean": 11.0, "latency_ms_mean": 663.6, "usd_sum": 0.00054 } }, { "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": 640, "output_tokens": 15, "latency_ms": 571.3, "usd": 0.00019, "model_version": "gpt-5.4-mini-2026-03-17", "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": 640, "output_tokens": 15, "latency_ms": 692.1, "usd": 0.00019, "model_version": "gpt-5.4-mini-2026-03-17", "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": 640, "output_tokens": 9, "latency_ms": 652.2, "usd": 0.000178, "model_version": "gpt-5.4-mini-2026-03-17", "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": 13.0, "latency_ms_mean": 638.533, "usd_sum": 0.000558 } }, { "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": 629, "output_tokens": 10, "latency_ms": 561.2, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "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": 629, "output_tokens": 10, "latency_ms": 625.2, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "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": 629, "output_tokens": 10, "latency_ms": 546.7, "usd": 0.000177, "model_version": "gpt-5.4-mini-2026-03-17", "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": 629.0, "output_tokens_mean": 10.0, "latency_ms_mean": 577.7, "usd_sum": 0.000531 } }, { "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": 631, "output_tokens": 12, "latency_ms": 625.4, "usd": 0.000182, "model_version": "gpt-5.4-mini-2026-03-17", "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": 631, "output_tokens": 12, "latency_ms": 632.2, "usd": 0.000182, "model_version": "gpt-5.4-mini-2026-03-17", "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": 631, "output_tokens": 12, "latency_ms": 575.0, "usd": 0.000182, "model_version": "gpt-5.4-mini-2026-03-17", "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": 12.0, "latency_ms_mean": 610.867, "usd_sum": 0.000546 } }, { "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": 634, "output_tokens": 10, "latency_ms": 548.0, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 634, "output_tokens": 10, "latency_ms": 582.4, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 634, "output_tokens": 10, "latency_ms": 620.8, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 10.0, "latency_ms_mean": 583.733, "usd_sum": 0.000537 } }, { "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": 634, "output_tokens": 10, "latency_ms": 706.0, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 634, "output_tokens": 10, "latency_ms": 628.9, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 634, "output_tokens": 10, "latency_ms": 630.4, "usd": 0.000179, "model_version": "gpt-5.4-mini-2026-03-17", "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": 10.0, "latency_ms_mean": 655.1, "usd_sum": 0.000537 } }, { "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": 633, "output_tokens": 10, "latency_ms": 653.9, "usd": 0.000178, "model_version": "gpt-5.4-mini-2026-03-17", "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": 633, "output_tokens": 10, "latency_ms": 596.6, "usd": 0.000178, "model_version": "gpt-5.4-mini-2026-03-17", "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": 633, "output_tokens": 10, "latency_ms": 768.6, "usd": 0.000178, "model_version": "gpt-5.4-mini-2026-03-17", "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": 633.0, "output_tokens_mean": 10.0, "latency_ms_mean": 673.033, "usd_sum": 0.000534 } }, { "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": 596, "output_tokens": 4, "latency_ms": 772.5, "usd": 0.000157, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 596, "output_tokens": 4, "latency_ms": 506.8, "usd": 0.000157, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 596, "output_tokens": 10, "latency_ms": 660.9, "usd": 0.000169, "model_version": "gpt-5.4-mini-2026-03-17", "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": 596.0, "output_tokens_mean": 6.0, "latency_ms_mean": 646.733, "usd_sum": 0.000483 } }, { "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": 586, "output_tokens": 4, "latency_ms": 618.9, "usd": 0.000155, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 586, "output_tokens": 10, "latency_ms": 573.5, "usd": 0.000167, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 586, "output_tokens": 4, "latency_ms": 791.3, "usd": 0.000155, "model_version": "gpt-5.4-mini-2026-03-17", "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": 586.0, "output_tokens_mean": 6.0, "latency_ms_mean": 661.233, "usd_sum": 0.000477 } }, { "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_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_sweetness_conflict", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 638, "output_tokens": 11, "latency_ms": 933.2, "usd": 0.000181, "model_version": "gpt-5.4-mini-2026-03-17", "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": 638, "output_tokens": 17, "latency_ms": 718.0, "usd": 0.000193, "model_version": "gpt-5.4-mini-2026-03-17", "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": 638, "output_tokens": 11, "latency_ms": 596.5, "usd": 0.000181, "model_version": "gpt-5.4-mini-2026-03-17", "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": 13.0, "latency_ms_mean": 749.233, "usd_sum": 0.000555 } }, { "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": 642, "output_tokens": 11, "latency_ms": 638.2, "usd": 0.000182, "model_version": "gpt-5.4-mini-2026-03-17", "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": 642, "output_tokens": 11, "latency_ms": 582.0, "usd": 0.000182, "model_version": "gpt-5.4-mini-2026-03-17", "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": 642, "output_tokens": 11, "latency_ms": 606.5, "usd": 0.000182, "model_version": "gpt-5.4-mini-2026-03-17", "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": 11.0, "latency_ms_mean": 608.9, "usd_sum": 0.000546 } }, { "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": 794, "output_tokens": 4, "latency_ms": 1524.5, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "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": 794, "output_tokens": 4, "latency_ms": 531.5, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "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": 794, "output_tokens": 4, "latency_ms": 541.3, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "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": 794.0, "output_tokens_mean": 4.0, "latency_ms_mean": 865.767, "usd_sum": 0.000621 } }, { "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": 795, "output_tokens": 4, "latency_ms": 555.5, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 579.9, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4, "latency_ms": 584.9, "usd": 0.000207, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 573.433, "usd_sum": 0.000621 } }, { "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": "5-63 °C", "compliant": true, "score": 1.0, "detail": { "predicted": "5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 788, "output_tokens": 8, "latency_ms": 606.8, "usd": 0.000213, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "5-63 °C", "compliant": true, "score": 1.0, "detail": { "predicted": "5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 788, "output_tokens": 8, "latency_ms": 532.2, "usd": 0.000213, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "5-63 °C", "compliant": true, "score": 1.0, "detail": { "predicted": "5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 788, "output_tokens": 8, "latency_ms": 823.4, "usd": 0.000213, "model_version": "gpt-5.4-mini-2026-03-17", "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": 788.0, "output_tokens_mean": 8.0, "latency_ms_mean": 654.133, "usd_sum": 0.000639 } }, { "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": 783, "output_tokens": 4, "latency_ms": 489.4, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 783, "output_tokens": 4, "latency_ms": 537.1, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 783, "output_tokens": 4, "latency_ms": 611.6, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 546.033, "usd_sum": 0.000612 } }, { "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": 782, "output_tokens": 4, "latency_ms": 10208.1, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 782, "output_tokens": 4, "latency_ms": 660.5, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 782, "output_tokens": 4, "latency_ms": 503.1, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 782.0, "output_tokens_mean": 4.0, "latency_ms_mean": 3790.567, "usd_sum": 0.000612 } }, { "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": 773, "output_tokens": 4, "latency_ms": 622.0, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "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": 773, "output_tokens": 4, "latency_ms": 618.7, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "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": 773, "output_tokens": 4, "latency_ms": 616.7, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 619.133, "usd_sum": 0.000603 } }, { "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": 777, "output_tokens": 5, "latency_ms": 594.1, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 777, "output_tokens": 5, "latency_ms": 703.7, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 777, "output_tokens": 5, "latency_ms": 563.9, "usd": 0.000204, "model_version": "gpt-5.4-mini-2026-03-17", "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": 777.0, "output_tokens_mean": 5.0, "latency_ms_mean": 620.567, "usd_sum": 0.000612 } }, { "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": 853, "output_tokens": 9, "latency_ms": 652.1, "usd": 0.000231, "model_version": "gpt-5.4-mini-2026-03-17", "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": 853, "output_tokens": 9, "latency_ms": 778.8, "usd": 0.000231, "model_version": "gpt-5.4-mini-2026-03-17", "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": 853, "output_tokens": 9, "latency_ms": 652.8, "usd": 0.000231, "model_version": "gpt-5.4-mini-2026-03-17", "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": 853.0, "output_tokens_mean": 9.0, "latency_ms_mean": 694.567, "usd_sum": 0.000693 } }, { "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": "set:receiving,storage_cold,prep,cooking,cooling,reheating,service", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "cooking", "cooling", "prep", "reheating", "service", "set:receiving", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.5714, "recall": 0.8 }, "metrics": { "input_tokens": 807, "output_tokens": 22, "latency_ms": 774.6, "usd": 0.000246, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "set:receiving,storage_cold,thawing,prep,cooking,cooling,reheating,service", "compliant": true, "score": 0.6154, "detail": { "predicted": [ "cooking", "cooling", "prep", "reheating", "service", "set:receiving", "storage_cold", "thawing" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.5, "recall": 0.8 }, "metrics": { "input_tokens": 807, "output_tokens": 26, "latency_ms": 746.0, "usd": 0.000254, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "set:receiving,storage_cold,thawing,prep,cooking,cooling,reheating,service", "compliant": true, "score": 0.6154, "detail": { "predicted": [ "cooking", "cooling", "prep", "reheating", "service", "set:receiving", "storage_cold", "thawing" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.5, "recall": 0.8 }, "metrics": { "input_tokens": 807, "output_tokens": 26, "latency_ms": 2757.6, "usd": 0.000254, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.6325, "score_summary": { "mean": 0.6325, "stdev": 0.0296, "sem": 0.0171, "ci95_lo": 0.599, "ci95_hi": 0.666, "n": 3 }, "score_if_valid": 0.6325, "format_rate": 1.0, "metrics": { "input_tokens_mean": 807.0, "output_tokens_mean": 24.667, "latency_ms_mean": 1426.067, "usd_sum": 0.000754 } }, { "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": 811, "output_tokens": 4, "latency_ms": 558.2, "usd": 0.000211, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 811, "output_tokens": 4, "latency_ms": 695.8, "usd": 0.000211, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 811, "output_tokens": 4, "latency_ms": 582.0, "usd": 0.000211, "model_version": "gpt-5.4-mini-2026-03-17", "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": 811.0, "output_tokens_mean": 4.0, "latency_ms_mean": 612.0, "usd_sum": 0.000633 } }, { "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": 860, "output_tokens": 9, "latency_ms": 8232.1, "usd": 0.000233, "model_version": "gpt-5.4-mini-2026-03-17", "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": 860, "output_tokens": 9, "latency_ms": 843.4, "usd": 0.000233, "model_version": "gpt-5.4-mini-2026-03-17", "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": 860, "output_tokens": 9, "latency_ms": 1429.6, "usd": 0.000233, "model_version": "gpt-5.4-mini-2026-03-17", "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": 860.0, "output_tokens_mean": 9.0, "latency_ms_mean": 3501.7, "usd_sum": 0.000699 } }, { "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": 829, "output_tokens": 14, "latency_ms": 606.5, "usd": 0.000235, "model_version": "gpt-5.4-mini-2026-03-17", "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": 829, "output_tokens": 14, "latency_ms": 591.1, "usd": 0.000235, "model_version": "gpt-5.4-mini-2026-03-17", "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": 829, "output_tokens": 14, "latency_ms": 701.7, "usd": 0.000235, "model_version": "gpt-5.4-mini-2026-03-17", "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": 829.0, "output_tokens_mean": 14.0, "latency_ms_mean": 633.1, "usd_sum": 0.000705 } }, { "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": 378, "output_tokens": 6, "latency_ms": 845.0, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 378, "output_tokens": 6, "latency_ms": 537.2, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8.5", "compliant": true, "score": 1.0, "detail": { "predicted": 8.5, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 378, "output_tokens": 6, "latency_ms": 596.5, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 6.0, "latency_ms_mean": 659.567, "usd_sum": 0.000321 } }, { "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": "9.5", "compliant": true, "score": 1.0, "detail": { "predicted": 9.5, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 360, "output_tokens": 6, "latency_ms": 506.4, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 0.0, "detail": { "predicted": 8.5, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 360, "output_tokens": 6, "latency_ms": 698.8, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "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": 360, "output_tokens": 6, "latency_ms": 599.4, "usd": 0.000102, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.5, "score_summary": { "mean": 0.5, "stdev": 0.5, "sem": 0.2887, "ci95_lo": -0.0658, "ci95_hi": 1.0658, "n": 3 }, "score_if_valid": 0.5, "format_rate": 1.0, "metrics": { "input_tokens_mean": 360.0, "output_tokens_mean": 6.0, "latency_ms_mean": 601.533, "usd_sum": 0.000306 } }, { "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": "8.5", "compliant": true, "score": 1.0, "detail": { "predicted": 8.5, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 348, "output_tokens": 6, "latency_ms": 621.5, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 1.0, "detail": { "predicted": 8.5, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 348, "output_tokens": 6, "latency_ms": 512.7, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8.5", "compliant": true, "score": 1.0, "detail": { "predicted": 8.5, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 348, "output_tokens": 6, "latency_ms": 524.0, "usd": 9.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 348.0, "output_tokens_mean": 6.0, "latency_ms_mean": 552.733, "usd_sum": 0.000297 } }, { "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": "{\"sweet\":8,\"sour\":4,\"salty\":0,\"bitter\":0.5,\"umami\":0}", "compliant": true, "score": 0.75, "detail": { "per_key": { "sweet": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "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": 566, "output_tokens": 30, "latency_ms": 642.2, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"sweet\":8,\"sour\":3,\"salty\":0,\"bitter\":0.5,\"umami\":0}", "compliant": true, "score": 0.65, "detail": { "per_key": { "sweet": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "sour": { "predicted": 3, "expected": 4.0, "score": 0.5 }, "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": 566, "output_tokens": 30, "latency_ms": 944.9, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"sweet\":8,\"sour\":3,\"salty\":0,\"bitter\":0.5,\"umami\":0}", "compliant": true, "score": 0.65, "detail": { "per_key": { "sweet": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "sour": { "predicted": 3, "expected": 4.0, "score": 0.5 }, "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": 566, "output_tokens": 30, "latency_ms": 857.8, "usd": 0.000201, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.6833, "score_summary": { "mean": 0.6833, "stdev": 0.0577, "sem": 0.0333, "ci95_lo": 0.618, "ci95_hi": 0.7487, "n": 3 }, "score_if_valid": 0.6833, "format_rate": 1.0, "metrics": { "input_tokens_mean": 566.0, "output_tokens_mean": 30.0, "latency_ms_mean": 814.967, "usd_sum": 0.000603 } }, { "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": "6.8", "compliant": true, "score": 0.8667, "detail": { "predicted": 6.8, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 364, "output_tokens": 6, "latency_ms": 738.7, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "6.8", "compliant": true, "score": 0.8667, "detail": { "predicted": 6.8, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 364, "output_tokens": 6, "latency_ms": 538.2, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "7.0", "compliant": true, "score": 1.0, "detail": { "predicted": 7.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 364, "output_tokens": 6, "latency_ms": 541.6, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.9111, "score_summary": { "mean": 0.9111, "stdev": 0.077, "sem": 0.0444, "ci95_lo": 0.824, "ci95_hi": 0.9982, "n": 3 }, "score_if_valid": 0.9111, "format_rate": 1.0, "metrics": { "input_tokens_mean": 364.0, "output_tokens_mean": 6.0, "latency_ms_mean": 606.167, "usd_sum": 0.000309 } }, { "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": "herbal", "compliant": true, "score": 0.0, "detail": { "predicted": "herbal", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 5, "latency_ms": 738.7, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 0.0, "detail": { "predicted": "herbal", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 5, "latency_ms": 618.4, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 0.0, "detail": { "predicted": "herbal", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 5, "latency_ms": 621.0, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 329.0, "output_tokens_mean": 5.0, "latency_ms_mean": 659.367, "usd_sum": 0.000276 } }, { "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": "{\"body\":4,\"acidity_perception\":8,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":1,\"effervescence\":9}", "compliant": true, "score": 0.75, "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": 1, "expected": 3.5, "score": 0.0 }, "effervescence": { "predicted": 9, "expected": 9.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 593, "output_tokens": 38, "latency_ms": 740.1, "usd": 0.000224, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"body\":4,\"acidity_perception\":7,\"tannin\":0,\"astringency\":0,\"alcohol_heat\":1,\"effervescence\":9}", "compliant": true, "score": 0.5833, "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": 0, "expected": 1.0, "score": 0.5 }, "alcohol_heat": { "predicted": 1, "expected": 3.5, "score": 0.0 }, "effervescence": { "predicted": 9, "expected": 9.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 593, "output_tokens": 38, "latency_ms": 865.7, "usd": 0.000224, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"body\":4,\"acidity_perception\":8,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":1,\"effervescence\":8}", "compliant": true, "score": 0.6667, "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": 1, "expected": 3.5, "score": 0.0 }, "effervescence": { "predicted": 8, "expected": 9.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 593, "output_tokens": 38, "latency_ms": 734.4, "usd": 0.000224, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.0834, "sem": 0.0481, "ci95_lo": 0.5723, "ci95_hi": 0.761, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 593.0, "output_tokens_mean": 38.0, "latency_ms_mean": 780.067, "usd_sum": 0.000672 } }, { "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": "8.0", "compliant": true, "score": 0.0, "detail": { "predicted": 8.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 355, "output_tokens": 6, "latency_ms": 549.6, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8.0", "compliant": true, "score": 0.0, "detail": { "predicted": 8.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 355, "output_tokens": 6, "latency_ms": 611.5, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 355, "output_tokens": 6, "latency_ms": 576.8, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.1111, "score_summary": { "mean": 0.1111, "stdev": 0.1924, "sem": 0.1111, "ci95_lo": -0.1067, "ci95_hi": 0.3289, "n": 3 }, "score_if_valid": 0.1111, "format_rate": 1.0, "metrics": { "input_tokens_mean": 355.0, "output_tokens_mean": 6.0, "latency_ms_mean": 579.3, "usd_sum": 0.000303 } }, { "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": "2.8", "compliant": true, "score": 0.0, "detail": { "predicted": 2.8, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 379, "output_tokens": 6, "latency_ms": 635.8, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "4.5", "compliant": true, "score": 0.0, "detail": { "predicted": 4.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 379, "output_tokens": 6, "latency_ms": 570.4, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "3.2", "compliant": true, "score": 0.0, "detail": { "predicted": 3.2, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 379, "output_tokens": 6, "latency_ms": 509.8, "usd": 0.000107, "model_version": "gpt-5.4-mini-2026-03-17", "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": 379.0, "output_tokens_mean": 6.0, "latency_ms_mean": 572.0, "usd_sum": 0.000321 } }, { "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": 357, "output_tokens": 6, "latency_ms": 700.5, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 357, "output_tokens": 6, "latency_ms": 614.0, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 357, "output_tokens": 6, "latency_ms": 567.0, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 357.0, "output_tokens_mean": 6.0, "latency_ms_mean": 627.167, "usd_sum": 0.000303 } }, { "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": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 330, "output_tokens": 6, "latency_ms": 603.2, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8.7", "compliant": true, "score": 0.8, "detail": { "predicted": 8.7, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 330, "output_tokens": 6, "latency_ms": 569.6, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 330, "output_tokens": 6, "latency_ms": 612.2, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7111, "score_summary": { "mean": 0.7111, "stdev": 0.077, "sem": 0.0444, "ci95_lo": 0.624, "ci95_hi": 0.7982, "n": 3 }, "score_if_valid": 0.7111, "format_rate": 1.0, "metrics": { "input_tokens_mean": 330.0, "output_tokens_mean": 6.0, "latency_ms_mean": 595.0, "usd_sum": 0.000282 } }, { "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": "{\"sweet\":7,\"sour\":4.5,\"salty\":0,\"bitter\":1.5,\"umami\":0}", "compliant": true, "score": 0.8, "detail": { "per_key": { "sweet": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "sour": { "predicted": 4.5, "expected": 5.5, "score": 0.5 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 1.5, "expected": 0.5, "score": 0.5 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 363, "output_tokens": 32, "latency_ms": 712.9, "usd": 0.000155, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"sweet\":7,\"sour\":5,\"salty\":0,\"bitter\":1,\"umami\":0}", "compliant": true, "score": 0.9, "detail": { "per_key": { "sweet": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "sour": { "predicted": 5, "expected": 5.5, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 1, "expected": 0.5, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 363, "output_tokens": 28, "latency_ms": 742.9, "usd": 0.000147, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"sweet\":7.5,\"sour\":4.5,\"salty\":0,\"bitter\":1,\"umami\":0}", "compliant": true, "score": 0.8, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 4.5, "expected": 5.5, "score": 0.5 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 1, "expected": 0.5, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 363, "output_tokens": 32, "latency_ms": 697.4, "usd": 0.000155, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.8333, "score_summary": { "mean": 0.8333, "stdev": 0.0577, "sem": 0.0333, "ci95_lo": 0.768, "ci95_hi": 0.8987, "n": 3 }, "score_if_valid": 0.8333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 363.0, "output_tokens_mean": 30.667, "latency_ms_mean": 717.733, "usd_sum": 0.000457 } }, { "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": "9.0", "compliant": true, "score": 1.0, "detail": { "predicted": 9.0, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 351, "output_tokens": 6, "latency_ms": 528.5, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "9.0", "compliant": true, "score": 1.0, "detail": { "predicted": 9.0, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 351, "output_tokens": 6, "latency_ms": 645.8, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 351, "output_tokens": 6, "latency_ms": 550.7, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "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": 351.0, "output_tokens_mean": 6.0, "latency_ms_mean": 575.0, "usd_sum": 0.0003 } }, { "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": "smoky", "compliant": true, "score": 0.0, "detail": { "predicted": "smoky", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 341, "output_tokens": 6, "latency_ms": 622.8, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "smoke", "compliant": true, "score": 0.0, "detail": { "predicted": "smoke", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 341, "output_tokens": 5, "latency_ms": 594.6, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "smoke", "compliant": true, "score": 0.0, "detail": { "predicted": "smoke", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 341, "output_tokens": 5, "latency_ms": 746.5, "usd": 9.5e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 341.0, "output_tokens_mean": 5.333, "latency_ms_mean": 654.633, "usd_sum": 0.000287 } }, { "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": "{\"body\":9,\"acidity_perception\":4,\"tannin\":7,\"astringency\":6,\"alcohol_heat\":6,\"effervescence\":0}", "compliant": true, "score": 0.625, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 4, "expected": 6.0, "score": 0.0 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 6, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 6, "expected": 8.5, "score": 0.0 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 370, "output_tokens": 38, "latency_ms": 690.1, "usd": 0.000169, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"body\":9,\"acidity_perception\":4,\"tannin\":7,\"astringency\":6,\"alcohol_heat\":7,\"effervescence\":0}", "compliant": true, "score": 0.6667, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 4, "expected": 6.0, "score": 0.0 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 6, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 7, "expected": 8.5, "score": 0.25 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 370, "output_tokens": 38, "latency_ms": 771.5, "usd": 0.000169, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"body\":9,\"acidity_perception\":4,\"tannin\":7,\"astringency\":6,\"alcohol_heat\":6,\"effervescence\":0}", "compliant": true, "score": 0.625, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 4, "expected": 6.0, "score": 0.0 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 6, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 6, "expected": 8.5, "score": 0.0 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 370, "output_tokens": 38, "latency_ms": 662.2, "usd": 0.000169, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.6389, "score_summary": { "mean": 0.6389, "stdev": 0.0241, "sem": 0.0139, "ci95_lo": 0.6117, "ci95_hi": 0.6661, "n": 3 }, "score_if_valid": 0.6389, "format_rate": 1.0, "metrics": { "input_tokens_mean": 370.0, "output_tokens_mean": 38.0, "latency_ms_mean": 707.933, "usd_sum": 0.000507 } }, { "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": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 369, "output_tokens": 6, "latency_ms": 762.1, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 369, "output_tokens": 6, "latency_ms": 699.7, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 369, "output_tokens": 6, "latency_ms": 620.9, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 369.0, "output_tokens_mean": 6.0, "latency_ms_mean": 694.233, "usd_sum": 0.000312 } }, { "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": 320, "output_tokens": 5, "latency_ms": 629.8, "usd": 9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 320, "output_tokens": 5, "latency_ms": 673.6, "usd": 9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 320, "output_tokens": 5, "latency_ms": 532.3, "usd": 9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 320.0, "output_tokens_mean": 5.0, "latency_ms_mean": 611.9, "usd_sum": 0.00027 } }, { "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": "3.5", "compliant": true, "score": 1.0, "detail": { "predicted": 3.5, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 352, "output_tokens": 6, "latency_ms": 723.1, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "3.5", "compliant": true, "score": 1.0, "detail": { "predicted": 3.5, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 352, "output_tokens": 6, "latency_ms": 738.1, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "3.5", "compliant": true, "score": 1.0, "detail": { "predicted": 3.5, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 352, "output_tokens": 6, "latency_ms": 547.4, "usd": 0.0001, "model_version": "gpt-5.4-mini-2026-03-17", "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": 6.0, "latency_ms_mean": 669.533, "usd_sum": 0.0003 } }, { "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": "{\"sweet\":2.0,\"sour\":7.5,\"salty\":4.5,\"bitter\":1.0,\"umami\":4.0}", "compliant": true, "score": 0.45, "detail": { "per_key": { "sweet": { "predicted": 2.0, "expected": 1.0, "score": 0.5 }, "sour": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "salty": { "predicted": 4.5, "expected": 6.0, "score": 0.25 }, "bitter": { "predicted": 1.0, "expected": 1.5, "score": 0.75 }, "umami": { "predicted": 4.0, "expected": 7.0, "score": 0.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 354, "output_tokens": 38, "latency_ms": 878.9, "usd": 0.000164, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"sweet\":3,\"sour\":8.5,\"salty\":4,\"bitter\":1,\"umami\":4.5}", "compliant": true, "score": 0.2, "detail": { "per_key": { "sweet": { "predicted": 3, "expected": 1.0, "score": 0.0 }, "sour": { "predicted": 8.5, "expected": 7.0, "score": 0.25 }, "salty": { "predicted": 4, "expected": 6.0, "score": 0.0 }, "bitter": { "predicted": 1, "expected": 1.5, "score": 0.75 }, "umami": { "predicted": 4.5, "expected": 7.0, "score": 0.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 354, "output_tokens": 32, "latency_ms": 707.8, "usd": 0.000152, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"sweet\":3,\"sour\":8.5,\"salty\":5,\"bitter\":1.5,\"umami\":4}", "compliant": true, "score": 0.35, "detail": { "per_key": { "sweet": { "predicted": 3, "expected": 1.0, "score": 0.0 }, "sour": { "predicted": 8.5, "expected": 7.0, "score": 0.25 }, "salty": { "predicted": 5, "expected": 6.0, "score": 0.5 }, "bitter": { "predicted": 1.5, "expected": 1.5, "score": 1.0 }, "umami": { "predicted": 4, "expected": 7.0, "score": 0.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 354, "output_tokens": 32, "latency_ms": 1022.1, "usd": 0.000152, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.1258, "sem": 0.0726, "ci95_lo": 0.1909, "ci95_hi": 0.4757, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 354.0, "output_tokens_mean": 34.0, "latency_ms_mean": 869.6, "usd_sum": 0.000468 } }, { "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": "2.5", "compliant": true, "score": 1.0, "detail": { "predicted": 2.5, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 344, "output_tokens": 6, "latency_ms": 599.5, "usd": 9.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "3.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 344, "output_tokens": 6, "latency_ms": 595.9, "usd": 9.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "2.5", "compliant": true, "score": 1.0, "detail": { "predicted": 2.5, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 344, "output_tokens": 6, "latency_ms": 570.5, "usd": 9.8e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 344.0, "output_tokens_mean": 6.0, "latency_ms_mean": 588.633, "usd_sum": 0.000294 } }, { "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": "{\"id\":\"ogs:core:ingredient:fleur-de-sel\",\"ogs_version\":\"0.1.0\",\"name\":\"Fleur de sel\",\"category\":\"salt\",\"sensory_profile\":{\"basic_tastes\":{\"salty\":8.5,\"sweet\":0,\"sour\":0,\"bitter\":0,\"umami\":0},\"structural\":{\"body\":1,\"acidity_perception\":0,\"tannin\":0,\"astringency\":0,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"marine\",\"group\":\"brine\",\"item\":\"sea salt\",\"intensity\":6}],\"texture\":[\"crisp\",\"delicate\",\"flaky\"],\"finish_length\":3,\"complexity\":2},\"notes\":\"Hand-harvested sea salt crystals with a delicate, briny character.\"}", "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": 2513, "output_tokens": 174, "latency_ms": 1156.6, "usd": 0.000976, "model_version": "gpt-5.4-mini-2026-03-17", "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 \"subcategory\": \"sea salt\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"salty\": 8.5\n },\n \"structural\": {\n \"body\": 2,\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 salt\",\n \"item\": \"briny\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"delicate\",\n \"crystalline\",\n \"flake\"\n ],\n \"finish_length\": 3,\n \"complexity\": 2\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": 2513, "output_tokens": 227, "latency_ms": 1527.0, "usd": 0.001082, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "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 \"subcategory\": \"sea salt\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"salty\": 7,\n \"sweet\": 0,\n \"sour\": 0,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 1,\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 salt\",\n \"item\": \"briny\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"crisp\",\n \"delicate\",\n \"flaky\"\n ],\n \"finish_length\": 3,\n \"complexity\": 2\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": 2513, "output_tokens": 257, "latency_ms": 1698.8, "usd": 0.001142, "model_version": "gpt-5.4-mini-2026-03-17", "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": 219.333, "latency_ms_mean": 1460.8, "usd_sum": 0.0032 } }, { "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\": \"Sauvignon Blanc\",\n \"region\": \"Loire Valley\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 5\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 7,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 1,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"white peach\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"grass\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"earth\",\n \"group\": \"minerality\",\n \"item\": \"flint\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"crisp\",\n \"light-bodied\",\n \"clean\"\n ],\n \"finish_length\": 6,\n \"complexity\": 6\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": 2514, "output_tokens": 373, "latency_ms": 1931.7, "usd": 0.001375, "model_version": "gpt-5.4-mini-2026-03-17", "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 \"subtype\": \"white 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\": 5,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 1,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"white peach\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"grass\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"green\",\n \"item\": \"gooseberry leaf\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"flint\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"crisp\",\n \"light-bodied\",\n \"linear\"\n ],\n \"finish_length\": 6,\n \"complexity\": 6\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": 2514, "output_tokens": 467, "latency_ms": 2442.0, "usd": 0.001563, "model_version": "gpt-5.4-mini-2026-03-17", "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\": \"Sauvignon Blanc\",\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\": 4,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 1,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"white peach\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"grass\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"mineral\",\n \"group\": \"flint\",\n \"item\": \"wet stone\",\n \"intensity\": 5\n }\n ],\n \"finish_length\": 6,\n \"complexity\": 6\n }\n}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'mineral' is not one of ['fruit', 'floral', 'herbal', 'spice', 'earth', 'wood', 'dairy', 'savory', 'confection', 'vegetal', 'marine']" ], "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": 2514, "output_tokens": 404, "latency_ms": 2040.0, "usd": 0.001437, "model_version": "gpt-5.4-mini-2026-03-17", "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": 2514.0, "output_tokens_mean": 414.667, "latency_ms_mean": 2137.9, "usd_sum": 0.004375 } }, { "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 and Champagne Pairing\",\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\": 95,\n \"primary\": true,\n \"description\": \"Effervescence and acidity cleanse the palate and cut through the creamy richness of brie.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 90,\n \"description\": \"The creamy, rich cheese and crisp, dry sparkling wine create a balanced mouthfeel.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 82,\n \"description\": \"Classic brie and brut Champagne share a refined, elegant profile that feels naturally aligned.\"\n }\n ],\n \"overall_score\": 94,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.5,\n \"detail\": \"Carbonation scrubs the palate between bites of creamy brie.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.3,\n \"detail\": \"Bright acidity cuts through the cheese's richness.\"\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.1,\n \"detail\": \"The wine's light body complements the bread-and-cheese composition.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.1,\n \"detail\": \"Dry, elegant flavors converge in a classic pairing style.\"\n }\n ],\n \"confidence\": 0.96\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": 3379, "output_tokens": 423, "latency_ms": 2677.2, "usd": 0.001691, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie and Champagne\",\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\": 95,\n \"primary\": true,\n \"description\": \"Effervescence and acidity cleanse the palate and cut through the creamy brie.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 88,\n \"description\": \"The beverage's acidity and light body balance the richness of the cheese and baguette.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 82,\n \"description\": \"Classic French pairing with complementary elegance and familiar flavor alignment.\"\n }\n ],\n \"overall_score\": 94,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.6,\n \"detail\": \"Bubbles scrub the palate between bites of creamy brie.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.3,\n \"detail\": \"Brut acidity brightens the rich cheese.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.1,\n \"detail\": \"Acidity helps balance the dish's richness.\"\n }\n ],\n \"confidence\": 0.96\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": 3379, "output_tokens": 368, "latency_ms": 2451.0, "usd": 0.001581, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie and Champagne Pairing\",\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\": 95,\n \"description\": \"Effervescence and acidity cleanse the palate against creamy brie.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 88,\n \"description\": \"The crisp, lean structure of brut Champagne balances the rich, creamy cheese.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 82,\n \"description\": \"Classic flavor and texture harmony between creamy brie and elegant sparkling wine.\"\n }\n ],\n \"overall_score\": 94,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.55,\n \"detail\": \"Bubbles scrub the palate and lift the creaminess of the brie.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.3,\n \"detail\": \"Champagne acidity cuts through the richness of the cheese.\"\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.15,\n \"detail\": \"The light, crisp body of brut Champagne matches the modest weight of brie on baguette.\"\n }\n ],\n \"confidence\": 0.96\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": 3379, "output_tokens": 374, "latency_ms": 2069.6, "usd": 0.001593, "model_version": "gpt-5.4-mini-2026-03-17", "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": 3379.0, "output_tokens_mean": 388.333, "latency_ms_mean": 2399.267, "usd_sum": 0.004865 } }, { "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": "{\"basic_tastes\":{\"sweet\":9,\"sour\":2,\"salty\":0,\"bitter\":0,\"umami\":0},\"structural\":{\"body\":6,\"acidity_perception\":2,\"tannin\":0,\"astringency\":0,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"tropical fruit\",\"intensity\":9},{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"stone fruit\",\"intensity\":7},{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"citrus\",\"intensity\":4},{\"family\":\"confection\",\"group\":\"candied\",\"item\":\"honey\",\"intensity\":5},{\"family\":\"floral\",\"group\":\"fresh\",\"item\":\"floral\",\"intensity\":3},{\"family\":\"vegetal\",\"group\":\"fresh\",\"item\":\"green\",\"intensity\":2}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 9, "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, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 712, "output_tokens": 188, "latency_ms": 1293.7, "usd": 0.000554, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"basic_tastes\":{\"sweet\":8.5,\"sour\":2,\"salty\":0,\"bitter\":0.5,\"umami\":0.5},\"structural\":{\"body\":5.5,\"acidity_perception\":2.5,\"tannin\":0.2,\"astringency\":0.3,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"tropical fruit\",\"intensity\":9},{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"mango\",\"intensity\":10},{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"stone fruit\",\"intensity\":6},{\"family\":\"fruit\",\"group\":\"candied\",\"item\":\"ripe fruit\",\"intensity\":4},{\"family\":\"floral\",\"group\":\"fresh\",\"item\":\"floral\",\"intensity\":2},{\"family\":\"herbal\",\"group\":\"fresh\",\"item\":\"green notes\",\"intensity\":1},{\"family\":\"confection\",\"group\":\"candied\",\"item\":\"honeyed\",\"intensity\":3}]}", "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": 5.5, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0.2, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 712, "output_tokens": 223, "latency_ms": 1266.1, "usd": 0.000624, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"basic_tastes\":{\"sweet\":8.5,\"sour\":2.5,\"salty\":0,\"bitter\":0.5,\"umami\":0.5},\"structural\":{\"body\":6.5,\"acidity_perception\":3,\"tannin\":0.5,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"mango\",\"intensity\":9.5},{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"tropical fruit\",\"intensity\":8},{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"stone fruit\",\"intensity\":4},{\"family\":\"fruit\",\"group\":\"candied\",\"item\":\"ripe fruit\",\"intensity\":5},{\"family\":\"floral\",\"group\":\"fresh\",\"item\":\"floral\",\"intensity\":2},{\"family\":\"confection\",\"group\":\"candied\",\"item\":\"honey\",\"intensity\":3},{\"family\":\"vegetal\",\"group\":\"fresh\",\"item\":\"green vegetal\",\"intensity\":2}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.5, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2.5, "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": 0.5, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 712, "output_tokens": 224, "latency_ms": 1571.1, "usd": 0.000626, "model_version": "gpt-5.4-mini-2026-03-17", "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": 712.0, "output_tokens_mean": 211.667, "latency_ms_mean": 1376.967, "usd_sum": 0.001804 } }, { "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 \"primary_language\": \"en\",\n \"name\": \"moules marinières\",\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 \"salty\": 4,\n \"umami\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8\n }\n ],\n \"texture\": [\n \"tender\",\n \"slippery\"\n ]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sour\": 3,\n \"salty\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"white fruit\",\n \"item\": \"white wine\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallots\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n }\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"role\": \"aromatic_garnish\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy herb\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ]\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"salty\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"rich\",\n \"silky\"\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 3,\n \"salty\": 4,\n \"bitter\": 1,\n \"umami\": 5\n },\n \"structural\": {\n \"body\": 4,\n \"acidity_perception\": 3,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8\n },\n {\n \"family\": \"fruit\",\n \"group\": \"white fruit\",\n \"item\": \"white wine\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"leafy herb\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"tender\",\n \"slippery\",\n \"silky\"\n ],\n \"finish_length\": 5,\n \"complexity\": 6\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": 3079, "output_tokens": 1100, "latency_ms": 4514.6, "usd": 0.00297, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"moules marinières\",\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 \"salty\": 3,\n \"umami\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8\n }\n ],\n \"texture\": [\n \"tender\",\n \"succulent\"\n ]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sour\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"grape\",\n \"item\": \"white wine\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\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 \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"soft\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"fresh\"\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\": 1,\n \"salty\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"silky\",\n \"rich\"\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sour\": 3,\n \"salty\": 4,\n \"umami\": 5,\n \"sweet\": 1\n },\n \"structural\": {\n \"body\": 4,\n \"acidity_perception\": 3,\n \"astringency\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8\n },\n {\n \"family\": \"fruit\",\n \"group\": \"grape\",\n \"item\": \"white wine\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"tender\",\n \"succulent\",\n \"brothy\",\n \"silky\"\n ],\n \"finish_length\": 5,\n \"complexity\": 6\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": 3079, "output_tokens": 1124, "latency_ms": 4680.4, "usd": 0.003018, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"moules marinières\",\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 \"salty\": 4,\n \"umami\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8\n }\n ],\n \"texture\": [\n \"tender\",\n \"succulent\"\n ]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sour\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"grape\",\n \"item\": \"white wine\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\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 \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n }\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"role\": \"aromatic_garnish\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ]\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"salty\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"silky\",\n \"rich\"\n ]\n }\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"proportion\": \"trace\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"salty\": 5,\n \"sour\": 3,\n \"umami\": 5,\n \"sweet\": 1\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 3,\n \"astringency\": 0,\n \"tannin\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8\n },\n {\n \"family\": \"fruit\",\n \"group\": \"grape\",\n \"item\": \"white wine\",\n \"intensity\": 4\n },\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"parsley\",\n \"intensity\": 4\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"tender\",\n \"succulent\",\n \"silky\",\n \"rich\"\n ],\n \"finish_length\": 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": 3079, "output_tokens": 1048, "latency_ms": 4520.5, "usd": 0.002866, "model_version": "gpt-5.4-mini-2026-03-17", "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": 3079.0, "output_tokens_mean": 1090.667, "latency_ms_mean": 4571.833, "usd_sum": 0.008854 } }, { "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 \"subcategory\": \"dried stigma\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 0,\n \"salty\": 0,\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\": \"floral\",\n \"group\": \"honey\",\n \"item\": \"hay\",\n \"intensity\": 4\n },\n {\n \"family\": \"spice\",\n \"group\": \"warm\",\n \"item\": \"earthy spice\",\n \"intensity\": 5\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"dry earth\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"fibrous\",\n \"dry\"\n ],\n \"finish_length\": 5,\n \"complexity\": 7\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": 2501, "output_tokens": 327, "latency_ms": 1749.9, "usd": 0.001279, "model_version": "gpt-5.4-mini-2026-03-17", "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 \"subcategory\": \"dried stigma\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"warm\",\n \"item\": \"hay\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"nectar\",\n \"item\": \"honey\",\n \"intensity\": 2\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"dry earth\",\n \"intensity\": 2\n }\n ],\n \"complexity\": 7,\n \"finish_length\": 6\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": 2501, "output_tokens": 246, "latency_ms": 1421.5, "usd": 0.001117, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:ingredient:saffron-stigma\",\"ogs_version\":\"0.1.0\",\"name\":\"saffron\",\"category\":\"spice\"}", "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": 2501, "output_tokens": 37, "latency_ms": 725.6, "usd": 0.000699, "model_version": "gpt-5.4-mini-2026-03-17", "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": 203.333, "latency_ms_mean": 1299.0, "usd_sum": 0.003095 } }, { "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\": \"other\",\n \"subcategory\": \"fermented soybean paste\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 2,\n \"salty\": 6.5,\n \"bitter\": 1,\n \"umami\": 8.5\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\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soybean\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"umami\",\n \"intensity\": 4\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"toasted\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"thick\",\n \"paste-like\"\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: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": "other", "expected": "other", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 330, "latency_ms": 2060.8, "usd": 0.001285, "model_version": "gpt-5.4-mini-2026-03-17", "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\": \"protein\",\n \"subcategory\": \"fermented soybean paste\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"salty\": 7.5,\n \"umami\": 8.5,\n \"sweet\": 1.5,\n \"sour\": 1,\n \"bitter\": 1\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 1.5,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soybean paste\",\n \"qualifier\": \"fermented\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"earthy\",\n \"intensity\": 3\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"malt\",\n \"qualifier\": \"cooked\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"thick\",\n \"smooth\",\n \"pasty\"\n ],\n \"finish_length\": 7,\n \"complexity\": 7\n }\n}", "compliant": true, "score": 0.5, "detail": { "schema_valid": true, "schema_errors": [], "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": "protein", "expected": "other", "match": false } } }, "metrics": { "input_tokens": 2501, "output_tokens": 359, "latency_ms": 1883.4, "usd": 0.001343, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"red miso\"\n },\n \"category\": \"other\",\n \"subcategory\": \"fermented soybean paste\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 7,\n \"bitter\": 0.5,\n \"umami\": 8\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"miso\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"umami\",\n \"intensity\": 4\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"toasted\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"thick\",\n \"paste-like\"\n ],\n \"finish_length\": 7,\n \"complexity\": 6\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "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": "other", "expected": "other", "match": true } } }, "metrics": { "input_tokens": 2501, "output_tokens": 334, "latency_ms": 1803.1, "usd": 0.001293, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.8333, "score_summary": { "mean": 0.8333, "stdev": 0.2887, "sem": 0.1667, "ci95_lo": 0.5067, "ci95_hi": 1.16, "n": 3 }, "score_if_valid": 0.8333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2501.0, "output_tokens_mean": 341.0, "latency_ms_mean": 1915.767, "usd_sum": 0.003921 } }, { "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": "{\"id\":\"ogs:core:ingredient:urfa-biber\",\"ogs_version\":\"0.1.0\",\"name\":\"Urfa chili\",\"category\":\"spice\",\"subcategory\":\"chili pepper\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":1,\"sour\":1,\"salty\":0,\"bitter\":1,\"umami\":1},\"structural\":{\"body\":3,\"acidity_perception\":1,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"spice\",\"group\":\"chili\",\"item\":\"red pepper\",\"qualifier\":\"dried\",\"intensity\":6},{\"family\":\"earth\",\"group\":\"soil\",\"item\":\"earthy\",\"intensity\":4},{\"family\":\"fruit\",\"group\":\"dried fruit\",\"item\":\"raisiny\",\"intensity\":3},{\"family\":\"smoke\",\"group\":\"smoke\",\"item\":\"smoky\",\"intensity\":2}],\"texture\":[\"flaky\",\"powdery\"],\"finish_length\":5,\"complexity\":6},\"notes\":\"Also known as Urfa biber; a Turkish chile pepper with deep, raisin-like heat and a dark, earthy profile.\"}", "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": 2500, "output_tokens": 252, "latency_ms": 1706.9, "usd": 0.001129, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Urfa chili\",\n \"category\": \"spice\",\n \"subcategory\": \"chili pepper\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 1,\n \"tannin\": 0,\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\": 7\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"earthy\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"qualifier\": \"dried\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"flaky\",\n \"slightly oily\"\n ],\n \"finish_length\": 6,\n \"complexity\": 7\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": 2500, "output_tokens": 344, "latency_ms": 1951.9, "usd": 0.001313, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Urfa chili\"\n },\n \"category\": \"spice\",\n \"subcategory\": \"dried chili pepper\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 4,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"pepper\",\n \"item\": \"red chili\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"sun-dried earthiness\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"intensity\": 3\n },\n {\n \"family\": \"smoke\",\n \"group\": \"smoke\",\n \"item\": \"smoky\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"crinkly\",\n \"coarse\"\n ],\n \"finish_length\": 5,\n \"complexity\": 6\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": 2500, "output_tokens": 373, "latency_ms": 1954.6, "usd": 0.001371, "model_version": "gpt-5.4-mini-2026-03-17", "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": 2500.0, "output_tokens_mean": 323.0, "latency_ms_mean": 1871.133, "usd_sum": 0.003813 } }, { "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": "{\"id\":\"ogs:core:ingredient:meyer-lemon\",\"ogs_version\":\"0.1.0\",\"name\":\"Meyer lemon\",\"category\":\"fruit\",\"subcategory\":\"citrus fruit\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3,\"sour\":6,\"salty\":0,\"bitter\":1,\"umami\":0},\"structural\":{\"body\":2,\"acidity_perception\":6.5,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"fresh\",\"intensity\":8},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"orange\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"floral\",\"group\":\"blossom\",\"item\":\"orange blossom\",\"intensity\":3},{\"family\":\"confection\",\"group\":\"honey\",\"item\":\"honey\",\"intensity\":2}],\"texture\":[\"juicy\",\"thin-skinned\"],\"finish_length\":5,\"complexity\":6},\"notes\":\"A sweeter, less sharply acidic lemon cultivar with fragrant citrus and floral notes.\"}", "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": 2500, "output_tokens": 247, "latency_ms": 1700.0, "usd": 0.001119, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:ingredient:meyer-lemon\",\"ogs_version\":\"0.1.0\",\"name\":\"Meyer lemon\",\"category\":\"fruit\",\"subcategory\":\"citrus\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3,\"sour\":6,\"salty\":0,\"bitter\":1,\"umami\":0},\"structural\":{\"body\":2,\"acidity_perception\":6.5,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"fresh\",\"intensity\":8},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"orange\",\"qualifier\":\"fresh\",\"intensity\":4},{\"family\":\"floral\",\"group\":\"blossom\",\"item\":\"honeysuckle\",\"intensity\":2},{\"family\":\"confection\",\"group\":\"sweet\",\"item\":\"honey\",\"intensity\":3}],\"texture\":[\"juicy\",\"succulent\"],\"finish_length\":5,\"complexity\":6},\"origin\":{\"region\":\"China\"},\"notes\":\"A sweeter, less sharply acidic lemon cultivar with fragrant citrus aroma and soft floral notes.\"}", "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": 2500, "output_tokens": 254, "latency_ms": 1583.0, "usd": 0.001133, "model_version": "gpt-5.4-mini-2026-03-17", "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 \"subcategory\": \"citrus\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 6,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\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\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"fresh\",\n \"intensity\": 8\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"orange\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"blossom\",\n \"item\": \"honeyed\",\n \"qualifier\": \"fresh\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"juicy\",\n \"succulent\"\n ],\n \"finish_length\": 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: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": 2500, "output_tokens": 349, "latency_ms": 1872.6, "usd": 0.001323, "model_version": "gpt-5.4-mini-2026-03-17", "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": 2500.0, "output_tokens_mean": 283.333, "latency_ms_mean": 1718.533, "usd_sum": 0.003575 } }, { "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\": \"wild huitlacoche\",\n \"category\": \"fungus\",\n \"subcategory\": \"corn smut\",\n \"description\": \"Edible fungal growth on corn ears, prized for its earthy, savory flavor.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0.5,\n \"salty\": 0.5,\n \"bitter\": 0.5,\n \"umami\": 7\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"earthy mushroom\",\n \"intensity\": 7\n },\n {\n \"family\": \"savory\",\n \"group\": \"brothy\",\n \"item\": \"umami broth\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"sweet corn\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"soft\",\n \"succulent\"\n ],\n \"finish_length\": 6,\n \"complexity\": 6\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": 2502, "output_tokens": 353, "latency_ms": 2351.7, "usd": 0.001332, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"wild huitlacoche\",\n \"category\": \"fungus\",\n \"subcategory\": \"corn smut\",\n \"description\": \"A fungal growth on corn ears, prized for its earthy, savory flavor.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 7\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"earthy\",\n \"intensity\": 7\n },\n {\n \"family\": \"savory\",\n \"group\": \"brothy\",\n \"item\": \"umami\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"sweet corn\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"soft\",\n \"moist\"\n ],\n \"finish_length\": 6,\n \"complexity\": 6\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": 2502, "output_tokens": 348, "latency_ms": 2192.8, "usd": 0.001321, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"wild huitlacoche\",\n \"category\": \"fungus\",\n \"subcategory\": \"corn smut\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 7\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 0.5,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"earthy mushroom\",\n \"intensity\": 7\n },\n {\n \"family\": \"savory\",\n \"group\": \"maillard\",\n \"item\": \"brothy umami\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"sweet corn\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"soft\",\n \"succulent\"\n ],\n \"finish_length\": 6,\n \"complexity\": 6\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": 2502, "output_tokens": 333, "latency_ms": 1912.1, "usd": 0.001292, "model_version": "gpt-5.4-mini-2026-03-17", "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": 344.667, "latency_ms_mean": 2152.2, "usd_sum": 0.003945 } }, { "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 \"sensory_profile\": {}\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": 2506, "output_tokens": 56, "latency_ms": 844.1, "usd": 0.000739, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Barolo\",\n \"type\": \"wine\",\n \"region\": \"Piedmont, Italy\",\n \"appellation\": \"Barolo DOCG\",\n \"grape_varieties\": [\n \"Nebbiolo\"\n ],\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 4,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 7,\n \"tannin\": 8,\n \"astringency\": 7,\n \"alcohol_heat\": 4,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"cherry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"dried cherry\",\n \"qualifier\": \"dried\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"flower\",\n \"item\": \"rose\",\n \"intensity\": 5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herb\",\n \"item\": \"dried herbs\",\n \"qualifier\": \"dried\",\n \"intensity\": 3\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"truffle\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"group\": \"sweet spice\",\n \"item\": \"licorice\",\n \"intensity\": 4\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"cedar\",\n \"intensity\": 3\n }\n ],\n \"finish_length\": 8.5,\n \"complexity\": 8.5\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": 2506, "output_tokens": 507, "latency_ms": 2527.5, "usd": 0.001641, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Barolo\",\n \"type\": \"wine\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 5,\n \"salty\": 0,\n \"bitter\": 4,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 6,\n \"tannin\": 8,\n \"astringency\": 7,\n \"alcohol_heat\": 4,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"cherry\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"raspberry\",\n \"intensity\": 4\n },\n {\n \"family\": \"floral\",\n \"group\": \"flower\",\n \"item\": \"rose\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"truffle\",\n \"intensity\": 4\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"licorice\",\n \"intensity\": 5\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"cedar\",\n \"intensity\": 3\n }\n ],\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": 2506, "output_tokens": 402, "latency_ms": 1973.4, "usd": 0.00143, "model_version": "gpt-5.4-mini-2026-03-17", "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": 2506.0, "output_tokens_mean": 321.667, "latency_ms_mean": 1781.667, "usd_sum": 0.00381 } }, { "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": "{\"id\":\"ogs:core:beverage:ardbeg-10-islay\",\"ogs_version\":\"0.1.0\",\"name\":\"Islay single malt\",\"type\":\"spirit\",\"subtype\":\"single malt whisky\",\"region\":\"Islay, Scotland\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":1,\"sour\":0.5,\"salty\":0,\"bitter\":1.5,\"umami\":0.5},\"structural\":{\"body\":7.5,\"acidity_perception\":1,\"tannin\":0.5,\"astringency\":2,\"alcohol_heat\":6,\"effervescence\":0},\"aromatics\":[{\"family\":\"smoke\",\"group\":\"peat\",\"item\":\"peat smoke\",\"intensity\":8.5},{\"family\":\"marine\",\"group\":\"iodine\",\"item\":\"sea spray\",\"intensity\":4.5},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"fresh\",\"intensity\":3},{\"family\":\"fruit\",\"group\":\"orchard\",\"item\":\"green apple\",\"qualifier\":\"fresh\",\"intensity\":2.5},{\"family\":\"spice\",\"group\":\"pepper\",\"item\":\"black pepper\",\"intensity\":3.5},{\"family\":\"earth\",\"group\":\"mineral\",\"item\":\"wet stone\",\"intensity\":3.5},{\"family\":\"wood\",\"group\":\"oak\",\"item\":\"smoked oak\",\"intensity\":4.5}],\"texture\":[\"oily\",\"smoky\",\"warming\"],\"finish_length\":8.5,\"complexity\":7.5}}", "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: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": 2512, "output_tokens": 323, "latency_ms": 1944.1, "usd": 0.001274, "model_version": "gpt-5.4-mini-2026-03-17", "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\": \"single malt whisky\",\n \"region\": \"Islay, Scotland\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 0.5,\n \"salty\": 0,\n \"bitter\": 2,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 1,\n \"tannin\": 1,\n \"astringency\": 2,\n \"alcohol_heat\": 6,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"smoke\",\n \"group\": \"smoke\",\n \"item\": \"peat smoke\",\n \"intensity\": 8\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"iodine\",\n \"intensity\": 6\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\": \"smoked oak\",\n \"intensity\": 4\n }\n ],\n \"finish_length\": 8,\n \"complexity\": 7\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: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": 2512, "output_tokens": 369, "latency_ms": 2054.6, "usd": 0.001366, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:beverage:ardbeg-10-islay\",\"ogs_version\":\"0.1.0\",\"name\":\"Islay single malt\",\"type\":\"spirit\",\"subtype\":\"single malt whisky\",\"region\":\"Islay, Scotland\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":2,\"sour\":0.5,\"salty\":0,\"bitter\":1.5,\"umami\":0},\"structural\":{\"body\":7,\"acidity_perception\":1,\"tannin\":0.5,\"astringency\":2,\"alcohol_heat\":6,\"effervescence\":0},\"aromatics\":[{\"family\":\"smoke\",\"group\":\"smoke\",\"item\":\"peat smoke\",\"intensity\":8},{\"family\":\"earth\",\"group\":\"earth\",\"item\":\"seaweed\",\"intensity\":4},{\"family\":\"marine\",\"group\":\"marine\",\"item\":\"brine\",\"intensity\":4},{\"family\":\"fruit\",\"group\":\"fruit\",\"item\":\"lemon\",\"qualifier\":\"fresh\",\"intensity\":2},{\"family\":\"fruit\",\"group\":\"fruit\",\"item\":\"apple\",\"qualifier\":\"fresh\",\"intensity\":2},{\"family\":\"wood\",\"group\":\"wood\",\"item\":\"oak\",\"qualifier\":\"toasted\",\"intensity\":3}],\"texture\":[\"oily\",\"viscous\"],\"finish_length\":8,\"complexity\":7}}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'toasted' is not one of ['fresh', 'dried', 'cooked', 'candied', 'fermented', 'zest', 'overripe']" ], "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": 2512, "output_tokens": 280, "latency_ms": 1686.2, "usd": 0.001188, "model_version": "gpt-5.4-mini-2026-03-17", "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": 2512.0, "output_tokens_mean": 324.0, "latency_ms_mean": 1894.967, "usd_sum": 0.003828 } }, { "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\": 2,\n \"sour\": 3,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 2\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 3,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 3,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"pear\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"orchard fruit\",\n \"item\": \"apple\",\n \"intensity\": 3\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"jasmine\",\n \"intensity\": 2\n },\n {\n \"family\": \"confection\",\n \"group\": \"sweet\",\n \"item\": \"rice\",\n \"intensity\": 3\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh\",\n \"item\": \"grass\",\n \"intensity\": 1\n }\n ],\n \"finish_length\": 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: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": 2515, "output_tokens": 382, "latency_ms": 2127.6, "usd": 0.001393, "model_version": "gpt-5.4-mini-2026-03-17", "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,\n \"sour\": 2,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 2\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 3,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 2,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"pear\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"orchard fruit\",\n \"item\": \"green apple\",\n \"intensity\": 3\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"jasmine\",\n \"intensity\": 2\n },\n {\n \"family\": \"confection\",\n \"group\": \"sweet\",\n \"item\": \"rice sweetness\",\n \"intensity\": 2\n }\n ],\n \"finish_length\": 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: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": 2515, "output_tokens": 352, "latency_ms": 2343.4, "usd": 0.001333, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:beverage:junmai-ginjo-generic\",\"ogs_version\":\"0.1.0\",\"name\":\"junmai ginjo sake\",\"type\":\"sake\",\"subtype\":\"junmai ginjo\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3,\"sour\":4,\"salty\":0,\"bitter\":1,\"umami\":2},\"structural\":{\"body\":3,\"acidity_perception\":4,\"tannin\":0,\"astringency\":0,\"alcohol_heat\":2,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"stone fruit\",\"item\":\"pear\",\"qualifier\":\"fresh\",\"intensity\":4},{\"family\":\"fruit\",\"group\":\"tree fruit\",\"item\":\"green apple\",\"qualifier\":\"fresh\",\"intensity\":3},{\"family\":\"floral\",\"group\":\"blossom\",\"item\":\"white flower\",\"qualifier\":\"fresh\",\"intensity\":2},{\"family\":\"confection\",\"group\":\"rice-derived\",\"item\":\"rice\",\"qualifier\":\"fresh\",\"intensity\":3},{\"family\":\"herbal\",\"group\":\"green\",\"item\":\"grass\",\"qualifier\":\"fresh\",\"intensity\":2}],\"texture\":[\"silky\",\"clean\"],\"finish_length\":5,\"complexity\":5}}", "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": 2515, "output_tokens": 264, "latency_ms": 1717.3, "usd": 0.001157, "model_version": "gpt-5.4-mini-2026-03-17", "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": 2515.0, "output_tokens_mean": 332.667, "latency_ms_mean": 2062.767, "usd_sum": 0.003883 } }, { "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 lager\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 2,\n \"effervescence\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"malt\",\n \"item\": \"toasted bread\",\n \"intensity\": 6\n },\n {\n \"family\": \"confection\",\n \"group\": \"malt\",\n \"item\": \"biscuit\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"light apricot\",\n \"intensity\": 2\n },\n {\n \"family\": \"spice\",\n \"group\": \"hop\",\n \"item\": \"mild herbal spice\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"smooth\",\n \"round\",\n \"moderately crisp\"\n ],\n \"finish_length\": 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: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": 2515, "output_tokens": 375, "latency_ms": 1830.1, "usd": 0.001379, "model_version": "gpt-5.4-mini-2026-03-17", "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 lager\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 2,\n \"effervescence\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"malt\",\n \"item\": \"bready malt\",\n \"intensity\": 7\n },\n {\n \"family\": \"confection\",\n \"group\": \"malt\",\n \"item\": \"toasty bread crust\",\n \"intensity\": 6\n },\n {\n \"family\": \"spice\",\n \"group\": \"hop\",\n \"item\": \"light herbal hop\",\n \"intensity\": 3\n }\n ],\n \"finish_length\": 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: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": 2515, "output_tokens": 318, "latency_ms": 2036.0, "usd": 0.001265, "model_version": "gpt-5.4-mini-2026-03-17", "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 \"subtype\": \"Märzen lager\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 2,\n \"effervescence\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"malt\",\n \"group\": \"grain\",\n \"item\": \"bready malt\",\n \"intensity\": 7\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"toffee\",\n \"intensity\": 4\n },\n {\n \"family\": \"spice\",\n \"group\": \"hop\",\n \"item\": \"light herbal hop\",\n \"intensity\": 2\n }\n ],\n \"finish_length\": 5,\n \"complexity\": 5\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": 2515, "output_tokens": 315, "latency_ms": 1662.5, "usd": 0.001259, "model_version": "gpt-5.4-mini-2026-03-17", "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": 2515.0, "output_tokens_mean": 336.0, "latency_ms_mean": 1842.867, "usd_sum": 0.003903 } }, { "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\": \"Crottin de Chavignol and Sancerre Blanc\",\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 \"primary\": true,\n \"description\": \"Classic Loire regional affinity with complementary fresh, tangy profiles.\"\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 88,\n \"description\": \"Both cheese and wine are light to medium in intensity, so neither overwhelms the other.\"\n },\n {\n \"type\": \"refresh\",\n \"score\": 90,\n \"description\": \"The wine's bright acidity refreshes the palate and cuts through the goat cheese.\"\n }\n ],\n \"overall_score\": 94,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.45,\n \"detail\": \"A classic Loire Valley pairing with strong regional affinity.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.25,\n \"detail\": \"Sancerre's citrus and mineral profile converges with the cheese's tangy freshness.\"\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.15,\n \"detail\": \"The wine and cheese are aligned in delicacy and overall presence.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.15,\n \"detail\": \"High acidity in the wine refreshes the palate and lifts the cheese.\"\n }\n ],\n \"confidence\": 0.95\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": 3381, "output_tokens": 433, "latency_ms": 2345.9, "usd": 0.001711, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Crottin de Chavignol and Sancerre Blanc\",\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 \"primary\": true,\n \"description\": \"Classic regional affinity and flavor convergence between Loire goat cheese and Sancerre blanc.\"\n },\n {\n \"type\": \"refresh\",\n \"score\": 90,\n \"description\": \"Bright acidity and mineral freshness cleanse the palate after the tangy, creamy cheese.\"\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 88,\n \"description\": \"The light-to-medium body of the wine aligns well with the delicate but expressive cheese.\"\n }\n ],\n \"overall_score\": 93,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.35,\n \"detail\": \"Both elements come from the Loire tradition, reinforcing terroir-driven compatibility.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.25,\n \"detail\": \"Citrus, mineral, and tangy dairy notes converge into a cohesive profile.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.2,\n \"detail\": \"The wine's acidity balances the cheese's richness and lactic tang.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.2,\n \"detail\": \"Acidity refreshes the palate and keeps each bite lively.\"\n }\n ],\n \"confidence\": 0.95\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": 3381, "output_tokens": 439, "latency_ms": 2355.9, "usd": 0.001723, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Crottin de Chavignol and Sancerre\",\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 \"primary\": true,\n \"description\": \"Classic regional affinity and shared bright, tangy profile create a seamless pairing.\"\n },\n {\n \"type\": \"refresh\",\n \"score\": 90,\n \"description\": \"The wine's acidity cleanses the palate and highlights the cheese's freshness.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 88,\n \"description\": \"The wine's lively acidity and light body balance the cheese's creamy tang.\"\n }\n ],\n \"overall_score\": 93,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.9,\n \"detail\": \"Both originate from the Loire region, reinforcing terroir-driven compatibility.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.85,\n \"detail\": \"Sancerre's citrus and mineral profile converges with the tangy, fresh goat cheese.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.9,\n \"detail\": \"High acidity in the wine refreshes the palate and cuts through the cheese's richness.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.86,\n \"detail\": \"The wine's acidity balances the cheese's lactic tang and creamy texture.\"\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.78,\n \"detail\": \"Both are medium-light in intensity, so neither overpowers the other.\"\n }\n ],\n \"confidence\": 0.97\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": 3381, "output_tokens": 484, "latency_ms": 2357.8, "usd": 0.001813, "model_version": "gpt-5.4-mini-2026-03-17", "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": 3381.0, "output_tokens_mean": 452.0, "latency_ms_mean": 2353.2, "usd_sum": 0.005247 } }, { "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": "{\"id\":\"ogs:core:dish:tonkotsu-ramen\",\"ogs_version\":\"0.1.0\",\"name\":\"tonkotsu ramen\",\"course\":\"main\",\"service_temperature\":\"hot\",\"components\":[{\"role\":\"sauce\",\"ingredient_ref\":\"ogs:core:ingredient:pork-bone-broth\",\"cooking_method\":\"braised\",\"proportion\":\"dominant\",\"sensory_contribution\":{\"basic_tastes\":{\"salty\":4.5,\"umami\":8.5,\"sweet\":1.0},\"aromatics\":[{\"family\":\"savory\",\"group\":\"broth\",\"item\":\"pork-bone broth\",\"intensity\":9},{\"family\":\"earth\",\"group\":\"animal\",\"item\":\"pork\",\"intensity\":4}],\"texture\":[\"rich\",\"creamy\",\"silky\"]}},{\"role\":\"starch\",\"ingredient_ref\":\"ogs:core:ingredient:wheat-noodles\",\"cooking_method\":\"boiled\",\"proportion\":\"significant\",\"sensory_contribution\":{\"basic_tastes\":{\"sweet\":0.5,\"salty\":0.5,\"umami\":0.5},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"grain\",\"item\":\"wheat\",\"intensity\":3}],\"texture\":[\"springy\",\"chewy\"]}},{\"role\":\"main_protein\",\"ingredient_ref\":\"ogs:core:ingredient:chashu\",\"cooking_method\":\"braised\",\"proportion\":\"significant\",\"sensory_contribution\":{\"basic_tastes\":{\"salty\":3,\"sweet\":1.5,\"umami\":4.5},\"aromatics\":[{\"family\":\"savory\",\"group\":\"pork\",\"item\":\"braised pork\",\"intensity\":6},{\"family\":\"spice\",\"group\":\"allium\",\"item\":\"garlic\",\"intensity\":1}],\"texture\":[\"tender\",\"succulent\"]}},{\"role\":\"main_protein\",\"ingredient_ref\":\"ogs:core:ingredient:soft-egg\",\"cooking_method\":\"poached\",\"proportion\":\"accent\",\"sensory_contribution\":{\"basic_tastes\":{\"sweet\":0.2,\"salty\":1,\"umami\":2.5},\"aromatics\":[{\"family\":\"dairy\",\"group\":\"egg\",\"item\":\"egg yolk\",\"intensity\":3}],\"texture\":[\"custardy\",\"soft\"]}},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:nori\",\"cooking_method\":\"dried\",\"proportion\":\"accent\",\"sensory_contribution\":{\"basic_tastes\":{\"salty\":1,\"umami\":1.5},\"aromatics\":[{\"family\":\"marine\",\"group\":\"seaweed\",\"item\":\"nori\",\"intensity\":4}],\"texture\":[\"crisp\",\"delicate\"]}},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:scallion\",\"cooking_method\":\"raw\",\"proportion\":\"accent\",\"sensory_contribution\":{\"basic_tastes\":{\"sweet\":0.2,\"bitter\":0.2},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"scallion\",\"intensity\":4}],\"texture\":[\"fresh\",\"crisp\"]}}],\"overall_sensory_profile\":{\"basic_tastes\":{\"sweet\":1.5,\"sour\":0.5,\"salty\":4.5,\"bitter\":0.5,\"umami\":8.5},\"structural\":{\"body\":8.5,\"acidity_perception\":1,\"tannin\":0,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"savory\",\"group\":\"broth\",\"item\":\"pork bone broth\",\"intensity\":9},{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"scallion\",\"intensity\":4},{\"family\":\"marine\",\"group\":\"seaweed\",\"item\":\"nori\",\"intensity\":4},{\"family\":\"savory\",\"group\":\"pork\",\"item\":\"braised pork\",\"intensity\":6},{\"family\":\"vegetal\",\"group\":\"grain\",\"item\":\"wheat\",\"intensity\":3}],\"texture\":[\"rich\",\"creamy\",\"silky\",\"springy\",\"chewy\",\"tender\",\"custardy\"],\"finish_length\":8.5,\"complexity\":7.5}}", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "'dried' 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": 3077, "output_tokens": 883, "latency_ms": 4110.7, "usd": 0.002535, "model_version": "gpt-5.4-mini-2026-03-17", "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:pork-bone-broth\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"umami\": 8.5,\n \"salty\": 5.5\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"broth\",\n \"item\": \"pork bone\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"dairy\",\n \"group\": \"broth\",\n \"item\": \"creamy\",\n \"intensity\": 6.5\n }\n ],\n \"texture\": [\n \"rich\",\n \"silky\"\n ]\n }\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:wheat-noodles\",\n \"cooking_method\": \"boiled\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {},\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 \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"umami\": 6.0,\n \"salty\": 3.0,\n \"sweet\": 1.0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"pork\",\n \"item\": \"braised pork\",\n \"intensity\": 6.5\n }\n ],\n \"texture\": [\n \"tender\",\n \"fatty\"\n ]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:soft-egg\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"umami\": 2.0,\n \"salty\": 1.0,\n \"sweet\": 0.5\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"egg\",\n \"item\": \"rich yolk\",\n \"intensity\": 3.0\n }\n ],\n \"texture\": [\n \"custardy\",\n \"jammy\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori\",\n \"cooking_method\": \"dehydrated\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 1.0,\n \"umami\": 1.5\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"crisp\",\n \"fragile\"\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 \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"intensity\": 3.5\n }\n ],\n \"texture\": [\n \"fresh\",\n \"crisp\"\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.0,\n \"sour\": 0.5,\n \"salty\": 5.5,\n \"bitter\": 0.5,\n \"umami\": 8.5\n },\n \"structural\": {\n \"body\": 8.5,\n \"acidity_perception\": 1.5,\n \"tannin\": 0.0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"pork broth\",\n \"item\": \"rich pork\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"dairy\",\n \"group\": \"broth\",\n \"item\": \"creamy\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"intensity\": 3.5\n }\n ],\n \"texture\": [\n \"rich\",\n \"silky\",\n \"springy noodles\",\n \"tender pork\",\n \"jammy egg\",\n \"crisp nori\"\n ],\n \"finish_length\": 7.5,\n \"complexity\": 7.0\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": 3077, "output_tokens": 1291, "latency_ms": 5818.2, "usd": 0.003351, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:dish:tonkotsu-ramen\",\"ogs_version\":\"0.1.0\",\"name\":\"tonkotsu ramen\",\"course\":\"main\",\"service_temperature\":\"hot\",\"components\":[{\"role\":\"sauce\",\"ingredient_ref\":\"ogs:core:ingredient:pork-bone-broth\",\"cooking_method\":\"braised\",\"proportion\":\"dominant\",\"sensory_contribution\":{\"basic_tastes\":{\"salty\":5.5,\"umami\":8.5,\"sweet\":1.5},\"aromatics\":[{\"family\":\"savory\",\"group\":\"pork\",\"item\":\"pork-bone broth\",\"intensity\":9},{\"family\":\"earth\",\"group\":\"mushroom\",\"item\":\"dried mushroom\",\"qualifier\":\"dried\",\"intensity\":1.5}],\"texture\":[\"rich\",\"silky\",\"brothy\"]}},{\"role\":\"starch\",\"ingredient_ref\":\"ogs:core:ingredient:wheat-noodles\",\"cooking_method\":\"boiled\",\"proportion\":\"significant\",\"sensory_contribution\":{\"texture\":[\"springy\",\"chewy\"]}},{\"role\":\"main_protein\",\"ingredient_ref\":\"ogs:core:ingredient:chashu\",\"cooking_method\":\"braised\",\"proportion\":\"significant\",\"sensory_contribution\":{\"basic_tastes\":{\"salty\":3,\"sweet\":2,\"umami\":4},\"aromatics\":[{\"family\":\"savory\",\"group\":\"pork\",\"item\":\"braised pork\",\"intensity\":6},{\"family\":\"wood\",\"group\":\"smoke\",\"item\":\"charred meat\",\"intensity\":1}],\"texture\":[\"tender\",\"fatty\"]}},{\"role\":\"main_protein\",\"ingredient_ref\":\"ogs:core:ingredient:soft-egg\",\"cooking_method\":\"poached\",\"proportion\":\"accent\",\"sensory_contribution\":{\"basic_tastes\":{\"salty\":1,\"sweet\":0.5,\"umami\":2},\"aromatics\":[{\"family\":\"dairy\",\"group\":\"egg\",\"item\":\"egg yolk\",\"intensity\":2}],\"texture\":[\"custardy\",\"jammy\"]}},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:nori\",\"proportion\":\"accent\",\"sensory_contribution\":{\"basic_tastes\":{\"salty\":1.5,\"umami\":1.5},\"aromatics\":[{\"family\":\"marine\",\"group\":\"seaweed\",\"item\":\"nori\",\"intensity\":3}],\"texture\":[\"crisp\",\"toasted\"]}},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:scallion\",\"role\":\"aromatic_garnish\",\"proportion\":\"accent\",\"sensory_contribution\":{\"basic_tastes\":{\"sweet\":0.5,\"sour\":0.2},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"scallion\",\"qualifier\":\"fresh\",\"intensity\":3}],\"texture\":[\"fresh\",\"crisp\"]}}],\"overall_sensory_profile\":{\"basic_tastes\":{\"sweet\":2,\"sour\":0.5,\"salty\":6,\"bitter\":0.5,\"umami\":8.5},\"structural\":{\"body\":8.5,\"acidity_perception\":1,\"tannin\":0,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"savory\",\"group\":\"pork\",\"item\":\"tonkotsu broth\",\"intensity\":9},{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"scallion\",\"qualifier\":\"fresh\",\"intensity\":3},{\"family\":\"marine\",\"group\":\"seaweed\",\"item\":\"nori\",\"intensity\":3},{\"family\":\"savory\",\"group\":\"pork\",\"item\":\"braised pork\",\"intensity\":6},{\"family\":\"dairy\",\"group\":\"egg\",\"item\":\"egg yolk\",\"intensity\":2}],\"texture\":[\"rich\",\"silky\",\"chewy\",\"tender\",\"custardy\"],\"finish_length\":8,\"complexity\":7.5}}", "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": 3077, "output_tokens": 837, "latency_ms": 4402.2, "usd": 0.002443, "model_version": "gpt-5.4-mini-2026-03-17", "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": 3077.0, "output_tokens_mean": 1003.667, "latency_ms_mean": 4777.033, "usd_sum": 0.008329 } }, { "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\": 2,\n \"sour\": 1,\n \"salty\": 0.5,\n \"bitter\": 0,\n \"umami\": 1.5\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"nightshade\",\n \"item\": \"tomato\",\n \"intensity\": 8\n }\n ],\n \"texture\": [\n \"juicy\",\n \"chunky\"\n ]\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,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\n \"crisp\"\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:cilantro\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"fresh herb\",\n \"item\": \"cilantro\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\n \"leafy\"\n ]\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\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"chile\",\n \"item\": \"jalapeño\",\n \"intensity\": 6,\n \"qualifier\": \"fresh\"\n }\n ],\n \"texture\": [\n \"crisp\"\n ]\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,\n \"sour\": 8,\n \"salty\": 0,\n \"bitter\": 0,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"zest\",\n \"intensity\": 6\n }\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 6.5,\n \"salty\": 1,\n \"bitter\": 0.5,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 7.5,\n \"tannin\": 0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"tomato\",\n \"item\": \"fresh tomato\",\n \"intensity\": 8\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"raw onion\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh herb\",\n \"item\": \"cilantro\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"chile\",\n \"item\": \"jalapeño\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"zest\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"fresh\",\n \"chunky\",\n \"juicy\",\n \"crisp\"\n ],\n \"finish_length\": 4,\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: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": 3062, "output_tokens": 1200, "latency_ms": 5237.1, "usd": 0.003165, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:dish:pico-de-gallo\",\"ogs_version\":\"0.1.0\",\"name\":\"pico de gallo\",\"components\":[{\"role\":\"main_vegetable\",\"ingredient_ref\":\"ogs:core:ingredient:tomato\",\"proportion\":\"dominant\",\"cooking_method\":\"raw\",\"sensory_contribution\":{\"basic_tastes\":{\"sweet\":2.5,\"sour\":1.5,\"salty\":0.5,\"umami\":1.5},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"nightshade\",\"item\":\"tomato\",\"intensity\":7.5},{\"family\":\"fruit\",\"group\":\"fresh\",\"item\":\"tomato\",\"intensity\":4.5}],\"texture\":[\"juicy\",\"soft\"]}},{\"role\":\"main_vegetable\",\"ingredient_ref\":\"ogs:core:ingredient:onion\",\"proportion\":\"significant\",\"cooking_method\":\"raw\",\"sensory_contribution\":{\"basic_tastes\":{\"sweet\":0.5,\"sour\":0.5,\"salty\":0.2,\"bitter\":0.2},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"onion\",\"intensity\":6.5}],\"texture\":[\"crisp\",\"sharp\"]}},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:cilantro\",\"proportion\":\"accent\",\"cooking_method\":\"raw\",\"sensory_contribution\":{\"basic_tastes\":{\"bitter\":0.5},\"aromatics\":[{\"family\":\"herbal\",\"group\":\"leafy\",\"item\":\"cilantro\",\"intensity\":6.0}],\"texture\":[\"fresh\",\"leafy\"]}},{\"role\":\"seasoning\",\"ingredient_ref\":\"ogs:core:ingredient:jalapeno\",\"proportion\":\"accent\",\"cooking_method\":\"raw\",\"sensory_contribution\":{\"basic_tastes\":{\"sweet\":0.2,\"sour\":0.2,\"salty\":0.2,\"bitter\":0.3},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"pepper\",\"item\":\"jalapeno\",\"intensity\":5.5},{\"family\":\"spice\",\"group\":\"pungent\",\"item\":\"capsaicin\",\"intensity\":4.5}],\"texture\":[\"crisp\",\"pungent\"]}},{\"role\":\"acid_component\",\"ingredient_ref\":\"ogs:core:ingredient:lime\",\"proportion\":\"accent\",\"cooking_method\":\"raw\",\"sensory_contribution\":{\"basic_tastes\":{\"sour\":6.5,\"sweet\":0.5,\"salty\":0.1,\"bitter\":0.2},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lime\",\"qualifier\":\"fresh\",\"intensity\":5.5}],\"texture\":[\"juicy\",\"bright\"]}}],\"overall_sensory_profile\":{\"basic_tastes\":{\"sweet\":2,\"sour\":5.5,\"salty\":1,\"bitter\":0.8,\"umami\":1.5},\"structural\":{\"body\":3,\"acidity_perception\":7.5,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"tomato\",\"item\":\"ripe tomato\",\"intensity\":7.5},{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"fresh onion\",\"intensity\":6.0},{\"family\":\"herbal\",\"group\":\"leafy\",\"item\":\"cilantro\",\"intensity\":6.0},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lime zest and juice\",\"qualifier\":\"fresh\",\"intensity\":5.5},{\"family\":\"spice\",\"group\":\"pungent\",\"item\":\"jalapeno heat\",\"intensity\":4.5}],\"texture\":[\"juicy\",\"crisp\",\"fresh\",\"chunky\"],\"finish_length\":4.5,\"complexity\":4.5}}", "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": 3062, "output_tokens": 815, "latency_ms": 4073.6, "usd": 0.002396, "model_version": "gpt-5.4-mini-2026-03-17", "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 \"course\": \"appetizer\",\n \"service_temperature\": \"cold\",\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,\n \"sour\": 1,\n \"salty\": 0.5,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"nightshade\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 8\n }\n ],\n \"texture\": [\n \"juicy\",\n \"chunky\"\n ]\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 },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\n \"crisp\"\n ]\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 \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"coriander\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n }\n ],\n \"texture\": [\n \"leafy\"\n ]\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\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"spice\",\n \"group\": \"chili\",\n \"item\": \"jalapeño\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"crisp\"\n ]\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,\n \"sour\": 7,\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\": 7\n }\n ]\n }\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 6,\n \"salty\": 0.5,\n \"bitter\": 0.5,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"tomato\",\n \"item\": \"ripe tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 8\n },\n {\n \"family\": \"herbal\",\n \"group\": \"cilantro\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"spice\",\n \"group\": \"chili\",\n \"item\": \"jalapeño\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\n \"fresh\",\n \"juicy\",\n \"chunky\",\n \"crisp\"\n ],\n \"finish_length\": 4,\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: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": 3062, "output_tokens": 1140, "latency_ms": 4598.8, "usd": 0.003046, "model_version": "gpt-5.4-mini-2026-03-17", "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": 3062.0, "output_tokens_mean": 1051.667, "latency_ms_mean": 4636.5, "usd_sum": 0.008607 } }, { "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": "{\"basic_tastes\":{\"sweet\":2,\"sour\":2.5,\"salty\":4.5,\"bitter\":0.5,\"umami\":7},\"structural\":{\"body\":7.5,\"acidity_perception\":2,\"tannin\":0,\"astringency\":0,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"dairy\",\"intensity\":8,\"qualifiers\":[\"cooked\"]},{\"family\":\"savory\",\"intensity\":7.5,\"qualifiers\":[]},{\"family\":\"fruit\",\"intensity\":4.5,\"qualifiers\":[\"dried\"]},{\"family\":\"nutty\",\"intensity\":6.5,\"qualifiers\":[]},{\"family\":\"wood\",\"intensity\":3.5,\"qualifiers\":[]},{\"family\":\"earth\",\"intensity\":2.5,\"qualifiers\":[]}] }", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 7, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 4.5, "expected": 5.0, "match": true }, "structural.body": { "predicted": 7.5, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 453, "output_tokens": 180, "latency_ms": 1413.2, "usd": 0.000473, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"basic_tastes\":{\"sweet\":2,\"sour\":1.5,\"salty\":4,\"bitter\":1,\"umami\":7.5},\"structural\":{\"body\":7,\"acidity_perception\":1.5,\"tannin\":0,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"dairy\",\"intensity\":8.5,\"qualifiers\":[\"cooked\"]},{\"family\":\"savory\",\"intensity\":8,\"qualifiers\":[\"cooked\"]},{\"family\":\"fruit\",\"intensity\":4,\"qualifiers\":[\"dried\"]},{\"family\":\"nutty\",\"intensity\":0}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 7.5, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 4, "expected": 5.0, "match": true }, "structural.body": { "predicted": 7, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 453, "output_tokens": 145, "latency_ms": 1095.6, "usd": 0.000403, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"basic_tastes\":{\"sweet\":2.5,\"sour\":1.5,\"salty\":4.5,\"bitter\":1.5,\"umami\":7.5},\"structural\":{\"body\":7.5,\"acidity_perception\":2.0,\"tannin\":0.0,\"astringency\":0.5,\"alcohol_heat\":0.0,\"effervescence\":0.0},\"aromatics\":[{\"family\":\"dairy\",\"qualifiers\":[\"cooked\"]},{\"family\":\"savory\",\"qualifiers\":[\"cooked\"]},{\"family\":\"nutty\",\"qualifiers\":[\"toasted\"]},{\"family\":\"fruit\",\"qualifiers\":[\"dried\"]},{\"family\":\"earth\",\"qualifiers\":[]},{\"family\":\"wood\",\"qualifiers\":[]}]}", "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": 7.5, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 453, "output_tokens": 160, "latency_ms": 1106.5, "usd": 0.000433, "model_version": "gpt-5.4-mini-2026-03-17", "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": 453.0, "output_tokens_mean": 161.667, "latency_ms_mean": 1205.1, "usd_sum": 0.001309 } }, { "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": "{\"basic_tastes\":{\"sweet\":1,\"sour\":0.5,\"salty\":2,\"bitter\":2,\"umami\":1},\"structural\":{\"body\":2,\"acidity_perception\":1,\"tannin\":0,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"vegetal\",\"qualifiers\":[\"cooked\",\"fresh\"]},{\"family\":\"earth\",\"qualifiers\":[\"cooked\"]},{\"family\":\"savory\",\"qualifiers\":[]},{\"family\":\"spice\",\"qualifiers\":[\"fresh\"]}]}", "compliant": true, "score": 0.6667, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 2, "expected": 5.0, "match": false }, "basic_tastes.bitter": { "predicted": 2, "expected": 3.0, "match": true }, "structural.body": { "predicted": 2, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 447, "output_tokens": 130, "latency_ms": 1198.6, "usd": 0.000372, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"basic_tastes\":{\"sweet\":1,\"sour\":1,\"salty\":2,\"bitter\":1,\"umami\":1},\"structural\":{\"body\":2,\"acidity_perception\":1,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"vegetal\",\"qualifiers\":[\"fresh\",\"cooked\"]},{\"family\":\"earth\",\"qualifiers\":[\"cooked\"]}]}", "compliant": true, "score": 0.6667, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 2, "expected": 5.0, "match": false }, "basic_tastes.bitter": { "predicted": 1, "expected": 3.0, "match": true }, "structural.body": { "predicted": 2, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 447, "output_tokens": 100, "latency_ms": 941.8, "usd": 0.000312, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"basic_tastes\":{\"sweet\":2,\"sour\":1,\"salty\":3,\"bitter\":2,\"umami\":1},\"structural\":{\"body\":2,\"acidity_perception\":1,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"vegetal\",\"qualifier\":\"fresh\"},{\"family\":\"vegetal\",\"qualifier\":\"cooked\"},{\"family\":\"earth\",\"qualifier\":\"fresh\"}]}", "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": 2, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 447, "output_tokens": 105, "latency_ms": 1003.9, "usd": 0.000322, "model_version": "gpt-5.4-mini-2026-03-17", "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": 447.0, "output_tokens_mean": 111.667, "latency_ms_mean": 1048.1, "usd_sum": 0.001006 } }, { "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": "{\"id\":\"ogs:core:pairing:mole-negro-garnacha\",\"ogs_version\":\"0.1.0\",\"name\":\"Mole Negro Enchiladas with Aragonese Garnacha\",\"dish_ref\":\"ogs:core:dish:mole-negro-enchiladas\",\"beverage_ref\":\"ogs:core:beverage:garnacha-aragon\",\"match_types\":[{\"type\":\"bridge\",\"score\":88,\"description\":\"Ripe red fruit and medium body bridge the deep mole sauce, while the wine's spice supports the chile-and-spice complexity.\",\"primary\":true},{\"type\":\"harmony\",\"score\":84,\"description\":\"The wine's fruit-forward profile and the dish's chocolate-chile richness converge into a warm, integrated flavor experience.\"},{\"type\":\"structural_balance\",\"score\":82,\"description\":\"Garnacha's supple body and moderate tannin align well with the weight and richness of mole negro enchiladas.\"},{\"type\":\"refresh\",\"score\":76,\"description\":\"Good acidity helps refresh the palate between bites of the rich sauce and filled tortillas.\"}],\"overall_score\":86,\"grade\":\"B+\",\"explanation_codes\":[{\"code\":\"AROMA_SHARED_FRUIT\",\"weight\":0.7,\"detail\":\"Red fruit in Garnacha links to the complex fruit notes that can echo through mole negro.\"},{\"code\":\"AROMA_SHARED_SPICE\",\"weight\":0.8,\"detail\":\"Spice tones in the wine connect with the chile, clove, and warming spice elements in the sauce.\"},{\"code\":\"HARMONY_FLAVOR_CONVERGE\",\"weight\":0.8,\"detail\":\"Both elements emphasize depth, warmth, and savoriness rather than sharp contrast.\"},{\"code\":\"STRUCT_BODY_ALIGN\",\"weight\":0.8,\"detail\":\"The wine's medium body suits the substantial texture of enchiladas with mole sauce.\"},{\"code\":\"REFRESH_ACID\",\"weight\":0.6,\"detail\":\"Acidity provides relief from the richness of the sauce and cheese.\"}],\"confidence\":0.83}", "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": 3371, "output_tokens": 412, "latency_ms": 2499.6, "usd": 0.001667, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:pairing:mole-negro-garnacha\",\"ogs_version\":\"0.1.0\",\"name\":\"Mole negro enchiladas with Aragonese Garnacha\",\"dish_ref\":\"ogs:core:dish:mole-negro-enchiladas\",\"beverage_ref\":\"ogs:core:beverage:garnacha-aragon\",\"match_types\":[{\"type\":\"bridge\",\"score\":86,\"description\":\"Ripe red fruit and supple body in Garnacha bridge the deep chocolate, chile, and spice complexity of mole negro.\",\"primary\":true},{\"type\":\"harmony\",\"score\":82,\"description\":\"Both dish and beverage offer warm, layered, savory-sweet richness that converges well across the pairing.\"},{\"type\":\"structural_balance\",\"score\":79,\"description\":\"Medium-bodied wine and sauce-driven enchiladas are close enough in weight to keep the pairing balanced.\"},{\"type\":\"refresh\",\"score\":74,\"description\":\"Garnacha's lively acidity helps refresh the palate between bites of rich mole.\"}],\"overall_score\":84,\"grade\":\"B\",\"explanation_codes\":[{\"code\":\"AROMA_SHARED_SPICE\",\"weight\":0.74,\"detail\":\"Spice and chile aromatics in the mole echo the wine's ripe, spicy profile.\"},{\"code\":\"AROMA_SHARED_FRUIT\",\"weight\":0.62,\"detail\":\"Red fruit notes in Garnacha create a fruit bridge into the dark sauce.\"},{\"code\":\"HARMONY_FLAVOR_CONVERGE\",\"weight\":0.8,\"detail\":\"The wine's warmth and fruit converge with the dish's savory-sweet depth.\"},{\"code\":\"STRUCT_BODY_ALIGN\",\"weight\":0.77,\"detail\":\"Garnacha's medium body supports the enchiladas without feeling thin or heavy.\"},{\"code\":\"STRUCT_ACIDITY_BALANCE\",\"weight\":0.7,\"detail\":\"Acidity in the wine lifts the richness of the mole.\"}],\"confidence\":0.78}", "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": 3371, "output_tokens": 398, "latency_ms": 2327.9, "usd": 0.001639, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:pairing:mole-negro-garnacha\",\"ogs_version\":\"0.1.0\",\"name\":\"Mole Negro Enchiladas with Aragonese Garnacha\",\"dish_ref\":\"ogs:core:dish:mole-negro-enchiladas\",\"beverage_ref\":\"ogs:core:beverage:garnacha-aragon\",\"match_types\":[{\"type\":\"bridge\",\"score\":88,\"description\":\"Ripe red fruit and moderate spice in the Garnacha bridge the chocolate-chile depth of mole negro while supporting its savory complexity.\",\"primary\":true},{\"type\":\"harmony\",\"score\":84,\"description\":\"Both dish and beverage are expressive and generous, creating a cohesive, full-flavored pairing.\",\"primary\":false},{\"type\":\"intensity_alignment\",\"score\":86,\"description\":\"The wine's body and fruit concentration are well matched to the richness and assertive seasoning of mole negro enchiladas.\",\"primary\":false},{\"type\":\"refresh\",\"score\":72,\"description\":\"The wine's freshness helps reset the palate between bites of the rich sauce and tortillas.\",\"primary\":false}],\"overall_score\":87,\"grade\":\"B+\",\"explanation_codes\":[{\"code\":\"AROMA_SHARED_FRUIT\",\"weight\":0.7,\"detail\":\"Red fruit notes in Garnacha provide an aromatic link to the sweet-spiced complexity of the mole.\"},{\"code\":\"AROMA_SHARED_SPICE\",\"weight\":0.8,\"detail\":\"The wine's spicy profile echoes the chile-and-spice character in mole negro.\"},{\"code\":\"HARMONY_COMPLEXITY_MATCH\",\"weight\":0.7,\"detail\":\"Both elements are layered and flavorful, so neither feels simplistic next to the other.\"},{\"code\":\"STRUCT_INTENSITY_MATCH\",\"weight\":0.8,\"detail\":\"The wine has enough body and flavor to stand up to the rich sauce without being overwhelmed.\"},{\"code\":\"STRUCT_BODY_ALIGN\",\"weight\":0.75,\"detail\":\"Medium-plus body in the wine aligns with the substantial texture of enchiladas and mole.\"},{\"code\":\"REFRESH_ACID\",\"weight\":0.65,\"detail\":\"Acidity in the wine helps lift the richness of the sauce and palate fatigue from the dish.\"}],\"risks\":[{\"code\":\"RISK_SPICE_ALCOHOL\",\"severity\":\"medium\",\"description\":\"If the Garnacha is too warm or alcohol-forward, it may amplify chile heat.\",\"mitigation\":\"Serve slightly cool and choose a balanced, not overly ripe, style.\"},{\"code\":\"RISK_INTENSITY_MISMATCH\",\"severity\":\"low\",\"description\":\"A lighter Garnacha could be overshadowed by the intensity of mole negro.\",\"mitigation\":\"Favor a more structured, fruit-rich example with good concentration.\"}],\"confidence\":0.84}", "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": 3371, "output_tokens": 559, "latency_ms": 3199.4, "usd": 0.001961, "model_version": "gpt-5.4-mini-2026-03-17", "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": 3371.0, "output_tokens_mean": 456.333, "latency_ms_mean": 2675.633, "usd_sum": 0.005267 } }, { "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": 332, "output_tokens": 4, "latency_ms": 490.7, "usd": 9.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 4, "latency_ms": 486.7, "usd": 9.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 4, "latency_ms": 640.2, "usd": 9.1e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 539.2, "usd_sum": 0.000273 } }, { "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": 324, "output_tokens": 4, "latency_ms": 669.7, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 324, "output_tokens": 4, "latency_ms": 602.7, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 324, "output_tokens": 4, "latency_ms": 620.1, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 324.0, "output_tokens_mean": 4.0, "latency_ms_mean": 630.833, "usd_sum": 0.000267 } }, { "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": 326, "output_tokens": 5, "latency_ms": 570.9, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 326, "output_tokens": 5, "latency_ms": 545.2, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 326, "output_tokens": 5, "latency_ms": 521.8, "usd": 9.2e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 326.0, "output_tokens_mean": 5.0, "latency_ms_mean": 545.967, "usd_sum": 0.000276 } }, { "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": 406, "output_tokens": 5, "latency_ms": 619.9, "usd": 0.000111, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 406, "output_tokens": 5, "latency_ms": 987.6, "usd": 0.000111, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 406, "output_tokens": 5, "latency_ms": 606.9, "usd": 0.000111, "model_version": "gpt-5.4-mini-2026-03-17", "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": 406.0, "output_tokens_mean": 5.0, "latency_ms_mean": 738.133, "usd_sum": 0.000333 } }, { "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": 316, "output_tokens": 5, "latency_ms": 825.6, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "harmony", "compliant": true, "score": 0.0, "detail": { "predicted": "harmony", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 316, "output_tokens": 5, "latency_ms": 656.2, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "bridge", "compliant": true, "score": 1.0, "detail": { "predicted": "bridge", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 316, "output_tokens": 4, "latency_ms": 825.6, "usd": 8.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 316.0, "output_tokens_mean": 4.667, "latency_ms_mean": 769.133, "usd_sum": 0.000265 } }, { "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": 350, "output_tokens": 5, "latency_ms": 570.7, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 350, "output_tokens": 5, "latency_ms": 581.8, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 350, "output_tokens": 5, "latency_ms": 622.9, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 591.8, "usd_sum": 0.000291 } }, { "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": 298, "output_tokens": 5, "latency_ms": 556.5, "usd": 8.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 298, "output_tokens": 5, "latency_ms": 495.7, "usd": 8.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 298, "output_tokens": 5, "latency_ms": 578.4, "usd": 8.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 298.0, "output_tokens_mean": 5.0, "latency_ms_mean": 543.533, "usd_sum": 0.000252 } }, { "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": 385, "output_tokens": 4, "latency_ms": 583.0, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 385, "output_tokens": 4, "latency_ms": 597.8, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 385, "output_tokens": 4, "latency_ms": 422.8, "usd": 0.000104, "model_version": "gpt-5.4-mini-2026-03-17", "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": 385.0, "output_tokens_mean": 4.0, "latency_ms_mean": 534.533, "usd_sum": 0.000312 } }, { "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": 331, "output_tokens": 5, "latency_ms": 627.4, "usd": 9.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 331, "output_tokens": 5, "latency_ms": 854.1, "usd": 9.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 331, "output_tokens": 5, "latency_ms": 750.7, "usd": 9.3e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 331.0, "output_tokens_mean": 5.0, "latency_ms_mean": 744.067, "usd_sum": 0.000279 } }, { "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": 328, "output_tokens": 4, "latency_ms": 612.8, "usd": 9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 328, "output_tokens": 4, "latency_ms": 550.2, "usd": 9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 328, "output_tokens": 4, "latency_ms": 493.0, "usd": 9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 328.0, "output_tokens_mean": 4.0, "latency_ms_mean": 552.0, "usd_sum": 0.00027 } }, { "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": "charred", "compliant": true, "score": 0.0, "detail": { "predicted": "charred", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 398, "output_tokens": 5, "latency_ms": 599.3, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "charred", "compliant": true, "score": 0.0, "detail": { "predicted": "charred", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 398, "output_tokens": 5, "latency_ms": 643.1, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "charred", "compliant": true, "score": 0.0, "detail": { "predicted": "charred", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 398, "output_tokens": 5, "latency_ms": 1585.9, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 942.767, "usd_sum": 0.00033 } }, { "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": 401, "output_tokens": 5, "latency_ms": 650.4, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 401, "output_tokens": 5, "latency_ms": 631.7, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 401, "output_tokens": 5, "latency_ms": 859.8, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 713.967, "usd_sum": 0.00033 } }, { "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": "sauce", "compliant": true, "score": 0.0, "detail": { "predicted": "sauce", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 346, "output_tokens": 5, "latency_ms": 769.2, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 346, "output_tokens": 5, "latency_ms": 995.9, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 346, "output_tokens": 5, "latency_ms": 592.1, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 346.0, "output_tokens_mean": 5.0, "latency_ms_mean": 785.733, "usd_sum": 0.000291 } }, { "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": "dried", "compliant": true, "score": 1.0, "detail": { "predicted": "dried", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 336, "output_tokens": 5, "latency_ms": 731.4, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "dried", "compliant": true, "score": 1.0, "detail": { "predicted": "dried", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 336, "output_tokens": 5, "latency_ms": 612.8, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "dried", "compliant": true, "score": 1.0, "detail": { "predicted": "dried", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 336, "output_tokens": 5, "latency_ms": 785.4, "usd": 9.4e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 336.0, "output_tokens_mean": 5.0, "latency_ms_mean": 709.867, "usd_sum": 0.000282 } }, { "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": 371, "output_tokens": 5, "latency_ms": 542.3, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 371, "output_tokens": 5, "latency_ms": 526.7, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 371, "output_tokens": 5, "latency_ms": 751.9, "usd": 0.000103, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 606.967, "usd_sum": 0.000309 } }, { "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": 313, "output_tokens": 4, "latency_ms": 753.3, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 313, "output_tokens": 4, "latency_ms": 1306.7, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 313, "output_tokens": 4, "latency_ms": 710.7, "usd": 8.6e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 923.567, "usd_sum": 0.000258 } }, { "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": 318, "output_tokens": 5, "latency_ms": 425.1, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 318, "output_tokens": 5, "latency_ms": 471.9, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 318, "output_tokens": 5, "latency_ms": 466.2, "usd": 8.9e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 318.0, "output_tokens_mean": 5.0, "latency_ms_mean": 454.4, "usd_sum": 0.000267 } }, { "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": 346, "output_tokens": 5, "latency_ms": 605.8, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 346, "output_tokens": 5, "latency_ms": 777.2, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 346, "output_tokens": 5, "latency_ms": 774.0, "usd": 9.7e-05, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 719.0, "usd_sum": 0.000291 } }, { "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": 400, "output_tokens": 5, "latency_ms": 538.0, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 400, "output_tokens": 5, "latency_ms": 1213.2, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 400, "output_tokens": 5, "latency_ms": 1114.2, "usd": 0.00011, "model_version": "gpt-5.4-mini-2026-03-17", "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": 5.0, "latency_ms_mean": 955.133, "usd_sum": 0.00033 } }, { "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": 371, "output_tokens": 4, "latency_ms": 726.5, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 371, "output_tokens": 4, "latency_ms": 516.3, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 371, "output_tokens": 4, "latency_ms": 720.8, "usd": 0.000101, "model_version": "gpt-5.4-mini-2026-03-17", "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": 4.0, "latency_ms_mean": 654.533, "usd_sum": 0.000303 } }, { "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": "[\"AROMA_SHARED_EARTH\",\"HARMONY_FLAVOR_CONVERGE\",\"STRUCT_TANNIN_FAT\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 1158, "output_tokens": 38, "latency_ms": 927.3, "usd": 0.000365, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_EARTH\",\"STRUCT_TANNIN_FAT\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.7273, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "STRUCT_ACIDITY_BALANCE", "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": 0.6667, "recall": 0.8 }, "metrics": { "input_tokens": 1158, "output_tokens": 43, "latency_ms": 9695.3, "usd": 0.000375, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\",\"STRUCT_TANNIN_FAT\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"STRUCT_UMAMI_ENHANCE\"]", "compliant": true, "score": 0.7273, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT", "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": 1158, "output_tokens": 43, "latency_ms": 926.0, "usd": 0.000375, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7515, "score_summary": { "mean": 0.7515, "stdev": 0.042, "sem": 0.0242, "ci95_lo": 0.704, "ci95_hi": 0.799, "n": 3 }, "score_if_valid": 0.7515, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1158.0, "output_tokens_mean": 41.333, "latency_ms_mean": 3849.533, "usd_sum": 0.001115 } }, { "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": "[\"REFRESH_ACID\",\"AROMA_SHARED_EARTH\",\"STRUCT_BODY_ALIGN\",\"STRUCT_ACIDITY_BALANCE\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.4, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "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": 1123, "output_tokens": 36, "latency_ms": 771.6, "usd": 0.000353, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"REFRESH_ACID\",\"REFRESH_MINERAL\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_BODY_ALIGN\",\"AROMA_SHARED_EARTH\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "REFRESH_ACID", "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": 1123, "output_tokens": 32, "latency_ms": 659.8, "usd": 0.000345, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_BODY_ALIGN\",\"REFRESH_ACID\",\"REFRESH_MINERAL\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "REFRESH_ACID", "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": 1123, "output_tokens": 32, "latency_ms": 610.0, "usd": 0.000345, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.5333, "score_summary": { "mean": 0.5333, "stdev": 0.1155, "sem": 0.0667, "ci95_lo": 0.4027, "ci95_hi": 0.664, "n": 3 }, "score_if_valid": 0.5333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1123.0, "output_tokens_mean": 33.333, "latency_ms_mean": 680.467, "usd_sum": 0.001043 } }, { "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": "[\"CONTRAST_RICH_CRISP\",\"REFRESH_EFFERVESCE\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.5714, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.5, "recall": 0.6667 }, "metrics": { "input_tokens": 1110, "output_tokens": 31, "latency_ms": 1067.4, "usd": 0.00034, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"CONTRAST_RICH_CRISP\",\"REFRESH_EFFERVESCE\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.5714, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.5, "recall": 0.6667 }, "metrics": { "input_tokens": 1110, "output_tokens": 31, "latency_ms": 672.1, "usd": 0.00034, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"CONTRAST_RICH_CRISP\",\"REFRESH_EFFERVESCE\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.5714, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.5, "recall": 0.6667 }, "metrics": { "input_tokens": 1110, "output_tokens": 33, "latency_ms": 899.3, "usd": 0.000344, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1110.0, "output_tokens_mean": 31.667, "latency_ms_mean": 879.6, "usd_sum": 0.001024 } }, { "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": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1130, "output_tokens": 36, "latency_ms": 1003.1, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1130, "output_tokens": 36, "latency_ms": 858.5, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"CONTRAST_RICH_CRISP\",\"CONTRAST_SWEET_ACID\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_SWEET_OFFSET\"]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1130, "output_tokens": 34, "latency_ms": 801.1, "usd": 0.000351, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.5463, "score_summary": { "mean": 0.5463, "stdev": 0.1764, "sem": 0.1019, "ci95_lo": 0.3466, "ci95_hi": 0.7459, "n": 3 }, "score_if_valid": 0.5463, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1130.0, "output_tokens_mean": 35.333, "latency_ms_mean": 887.567, "usd_sum": 0.001059 } }, { "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": "[\"AROMA_SHARED_SPICE\",\"AROMA_SHARED_WOOD\",\"HARMONY_FLAVOR_CONVERGE\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "HARMONY_FLAVOR_CONVERGE", "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": 1135, "output_tokens": 37, "latency_ms": 714.7, "usd": 0.000358, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_SPICE\",\"AROMA_SHARED_WOOD\",\"HARMONY_FLAVOR_CONVERGE\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "HARMONY_FLAVOR_CONVERGE", "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": 1135, "output_tokens": 39, "latency_ms": 793.4, "usd": 0.000362, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_SPICE\",\"AROMA_SHARED_WOOD\",\"STRUCT_TANNIN_FAT\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "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": 1135, "output_tokens": 38, "latency_ms": 624.8, "usd": 0.00036, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1135.0, "output_tokens_mean": 38.0, "latency_ms_mean": 710.967, "usd_sum": 0.00108 } }, { "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\",\"CONTRAST_SWEET_ACID\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_TANNIN_FAT\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1126, "output_tokens": 39, "latency_ms": 777.4, "usd": 0.00036, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"HARMONY_FLAVOR_CONVERGE\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_TANNIN_FAT\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1126, "output_tokens": 39, "latency_ms": 775.9, "usd": 0.00036, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"AROMA_SHARED_FRUIT\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_TANNIN_FAT\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1126, "output_tokens": 36, "latency_ms": 872.2, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1126.0, "output_tokens_mean": 38.0, "latency_ms_mean": 808.5, "usd_sum": 0.001074 } }, { "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": "[\"AROMA_SHARED_SPICE\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1117, "output_tokens": 38, "latency_ms": 636.5, "usd": 0.000355, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"CONTRAST_SWEET_ACID\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1117, "output_tokens": 38, "latency_ms": 766.8, "usd": 0.000355, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_SWEET_ACID\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_ACID", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1117, "output_tokens": 39, "latency_ms": 789.4, "usd": 0.000357, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1117.0, "output_tokens_mean": 38.333, "latency_ms_mean": 730.9, "usd_sum": 0.001067 } }, { "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_SPICE\",\"STRUCT_TANNIN_FAT\",\"STRUCT_BODY_ALIGN\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1114, "output_tokens": 36, "latency_ms": 675.3, "usd": 0.000351, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"AROMA_SHARED_EARTH\",\"STRUCT_TANNIN_FAT\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1114, "output_tokens": 40, "latency_ms": 673.5, "usd": 0.000358, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "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": 1114, "output_tokens": 41, "latency_ms": 769.1, "usd": 0.00036, "model_version": "gpt-5.4-mini-2026-03-17", "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": 39.0, "latency_ms_mean": 705.967, "usd_sum": 0.001069 } }, { "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": "[\"AROMA_SHARED_HERBAL\",\"CONTRAST_SWEET_ACID\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1114, "output_tokens": 37, "latency_ms": 749.3, "usd": 0.000353, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"CONTRAST_SWEET_ACID\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1114, "output_tokens": 37, "latency_ms": 764.7, "usd": 0.000353, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"CONTRAST_SWEET_ACID\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1114, "output_tokens": 37, "latency_ms": 924.4, "usd": 0.000353, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1114.0, "output_tokens_mean": 37.0, "latency_ms_mean": 812.8, "usd_sum": 0.001059 } }, { "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\",\"HARMONY_FLAVOR_CONVERGE\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1110, "output_tokens": 38, "latency_ms": 929.3, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_EARTH\",\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1110, "output_tokens": 38, "latency_ms": 741.5, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\",\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.75, "recall": 0.6 }, "metrics": { "input_tokens": 1110, "output_tokens": 29, "latency_ms": 745.3, "usd": 0.000336, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.6222, "score_summary": { "mean": 0.6222, "stdev": 0.0385, "sem": 0.0222, "ci95_lo": 0.5787, "ci95_hi": 0.6658, "n": 3 }, "score_if_valid": 0.6222, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1110.0, "output_tokens_mean": 35.0, "latency_ms_mean": 805.367, "usd_sum": 0.001044 } }, { "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": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_RICH_CRISP\",\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\",\"STRUCT_SWEET_OFFSET\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1116, "output_tokens": 37, "latency_ms": 906.7, "usd": 0.000353, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_RICH_CRISP\",\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1116, "output_tokens": 37, "latency_ms": 924.5, "usd": 0.000353, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_RICH_CRISP\",\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1116, "output_tokens": 38, "latency_ms": 939.3, "usd": 0.000355, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.7408, "score_summary": { "mean": 0.7408, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.5956, "ci95_hi": 0.8859, "n": 3 }, "score_if_valid": 0.7408, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1116.0, "output_tokens_mean": 37.333, "latency_ms_mean": 923.5, "usd_sum": 0.001061 } }, { "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": "[\"AROMA_SHARED_EARTH\",\"AROMA_SHARED_WOOD\",\"STRUCT_TANNIN_FAT\",\"STRUCT_BODY_ALIGN\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_WOOD", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1113, "output_tokens": 37, "latency_ms": 950.5, "usd": 0.000352, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_EARTH\",\"AROMA_SHARED_WOOD\",\"STRUCT_TANNIN_FAT\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_WOOD", "HARMONY_FLAVOR_CONVERGE", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1113, "output_tokens": 33, "latency_ms": 691.5, "usd": 0.000344, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\",\"HARMONY_COMPLEXITY_MATCH\",\"STRUCT_TANNIN_FAT\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "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": 1113, "output_tokens": 36, "latency_ms": 674.3, "usd": 0.00035, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.537, "score_summary": { "mean": 0.537, "stdev": 0.1157, "sem": 0.0668, "ci95_lo": 0.4061, "ci95_hi": 0.6679, "n": 3 }, "score_if_valid": 0.537, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1113.0, "output_tokens_mean": 35.333, "latency_ms_mean": 772.1, "usd_sum": 0.001046 } }, { "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_WOOD\",\"CONTRAST_TEMP_TEXTURE\",\"STRUCT_TANNIN_FAT\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.0, "detail": { "predicted": [ "AROMA_SHARED_WOOD", "CONTRAST_TEMP_TEXTURE", "REFRESH_ACID", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.0, "recall": 0.0 }, "metrics": { "input_tokens": 1119, "output_tokens": 28, "latency_ms": 831.0, "usd": 0.000336, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_WOOD\",\"CONTRAST_RICH_CRISP\",\"REFRESH_ACID\",\"STRUCT_TANNIN_FAT\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_WOOD", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1119, "output_tokens": 36, "latency_ms": 564.2, "usd": 0.000352, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_WOOD\",\"STRUCT_TANNIN_FAT\",\"REFRESH_ACID\",\"REFRESH_MINERAL\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1119, "output_tokens": 33, "latency_ms": 647.1, "usd": 0.000346, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.2222, "score_summary": { "mean": 0.2222, "stdev": 0.2222, "sem": 0.1283, "ci95_lo": -0.0292, "ci95_hi": 0.4736, "n": 3 }, "score_if_valid": 0.2222, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1119.0, "output_tokens_mean": 32.333, "latency_ms_mean": 680.767, "usd_sum": 0.001034 } }, { "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_PROTEIN\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "AROMA_SHARED_SPICE", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "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": 1119, "output_tokens": 37, "latency_ms": 639.4, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "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": 1119, "output_tokens": 33, "latency_ms": 909.0, "usd": 0.000346, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"HARMONY_FLAVOR_CONVERGE\",\"STRUCT_BODY_ALIGN\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "HARMONY_FLAVOR_CONVERGE", "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": 1119, "output_tokens": 37, "latency_ms": 731.6, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1119.0, "output_tokens_mean": 35.667, "latency_ms_mean": 760.0, "usd_sum": 0.001054 } }, { "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": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_BODY_ALIGN\",\"STRUCT_TANNIN_FAT\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_FAT" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1106, "output_tokens": 37, "latency_ms": 674.5, "usd": 0.000351, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\"]", "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": 1106, "output_tokens": 36, "latency_ms": 640.7, "usd": 0.000349, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_TANNIN_FAT\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_FAT" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1106, "output_tokens": 39, "latency_ms": 914.8, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1106.0, "output_tokens_mean": 37.333, "latency_ms_mean": 743.333, "usd_sum": 0.001054 } }, { "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_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"CONTRAST_TEMP_TEXTURE\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.2, "detail": { "predicted": [ "CONTRAST_TEMP_TEXTURE", "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": 1113, "output_tokens": 34, "latency_ms": 708.6, "usd": 0.000346, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"CONTRAST_TEMP_TEXTURE\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "CONTRAST_TEMP_TEXTURE", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.25, "recall": 0.2 }, "metrics": { "input_tokens": 1113, "output_tokens": 29, "latency_ms": 724.6, "usd": 0.000336, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"CONTRAST_TEMP_TEXTURE\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "CONTRAST_TEMP_TEXTURE", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.25, "recall": 0.2 }, "metrics": { "input_tokens": 1113, "output_tokens": 25, "latency_ms": 763.0, "usd": 0.000328, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.2148, "score_summary": { "mean": 0.2148, "stdev": 0.0128, "sem": 0.0074, "ci95_lo": 0.2003, "ci95_hi": 0.2293, "n": 3 }, "score_if_valid": 0.2148, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1113.0, "output_tokens_mean": 29.333, "latency_ms_mean": 732.067, "usd_sum": 0.00101 } }, { "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\",\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "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": 1118, "output_tokens": 38, "latency_ms": 820.6, "usd": 0.000356, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "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": 1118, "output_tokens": 38, "latency_ms": 951.5, "usd": 0.000356, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "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": 1118, "output_tokens": 38, "latency_ms": 662.4, "usd": 0.000356, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1118.0, "output_tokens_mean": 38.0, "latency_ms_mean": 811.5, "usd_sum": 0.001068 } }, { "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_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "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": 1120, "output_tokens": 38, "latency_ms": 908.8, "usd": 0.000356, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_SWEET_OFFSET\",\"AROMA_SHARED_FRUIT\",\"HARMONY_FLAVOR_CONVERGE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "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": 1120, "output_tokens": 37, "latency_ms": 783.5, "usd": 0.000354, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "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": 1120, "output_tokens": 38, "latency_ms": 800.0, "usd": 0.000356, "model_version": "gpt-5.4-mini-2026-03-17", "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": 1120.0, "output_tokens_mean": 37.667, "latency_ms_mean": 830.767, "usd_sum": 0.001066 } }, { "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_WOOD\",\"STRUCT_TANNIN_FAT\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_ALCOHOL_WARMTH\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_WOOD", "STRUCT_ALCOHOL_WARMTH", "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": 1123, "output_tokens": 38, "latency_ms": 758.2, "usd": 0.000357, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_EARTH\",\"AROMA_SHARED_WOOD\",\"STRUCT_TANNIN_FAT\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_ALCOHOL_WARMTH\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "AROMA_SHARED_WOOD", "STRUCT_ALCOHOL_WARMTH", "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": 1123, "output_tokens": 38, "latency_ms": 883.8, "usd": 0.000357, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_EARTH\",\"HARMONY_REGIONAL\",\"STRUCT_TANNIN_FAT\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_ALCOHOL_WARMTH\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ALCOHOL_WARMTH", "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": 1123, "output_tokens": 38, "latency_ms": 741.4, "usd": 0.000357, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.2222, "score_summary": { "mean": 0.2222, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.2222, "ci95_hi": 0.2222, "n": 3 }, "score_if_valid": 0.2222, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1123.0, "output_tokens_mean": 38.0, "latency_ms_mean": 794.467, "usd_sum": 0.001071 } }, { "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": "[\"STRUCT_TANNIN_FAT\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\",\"HARMONY_FLAVOR_CONVERGE\",\"CONTRAST_RICH_CRISP\"]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_FLAVOR_CONVERGE", "REFRESH_ACID", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_FAT" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1110, "output_tokens": 39, "latency_ms": 724.4, "usd": 0.000356, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 1, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"CONTRAST_RICH_CRISP\",\"AROMA_SHARED_FRUIT\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "STRUCT_BODY_ALIGN", "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": 1110, "output_tokens": 34, "latency_ms": 703.4, "usd": 0.000345, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } }, { "sample": 2, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"STRUCT_BODY_ALIGN\",\"CONTRAST_RICH_CRISP\",\"AROMA_SHARED_FRUIT\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1110, "output_tokens": 37, "latency_ms": 823.0, "usd": 0.000352, "model_version": "gpt-5.4-mini-2026-03-17", "finish_reason": "stop" } } ], "score": 0.3703, "score_summary": { "mean": 0.3703, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.2252, "ci95_hi": 0.5155, "n": 3 }, "score_if_valid": 0.3703, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1110.0, "output_tokens_mean": 36.667, "latency_ms_mean": 750.267, "usd_sum": 0.001053 } } ], "category_scores": { "composition": { "mean_score": 0.7829, "ci95_lo": 0.618, "ci95_hi": 0.9478, "stdev": 0.3763, "task_count": 20, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.7829 }, "dietary": { "mean_score": 0.6536, "ci95_lo": 0.4781, "ci95_hi": 0.8292, "stdev": 0.3102, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.6536 }, "explanation": { "mean_score": 0.541, "ci95_lo": 0.463, "ci95_hi": 0.6191, "stdev": 0.1781, "task_count": 20, "weight": 0.1, "format_rate": 1.0, "score_if_valid": 0.541 }, "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": 0.4161, "ci95_lo": 0.1566, "ci95_hi": 0.6756, "stdev": 0.4187, "task_count": 10, "weight": 0.03, "format_rate": 1.0, "score_if_valid": 0.4161 }, "pairing": { "mean_score": 0.9735, "ci95_lo": 0.9376, "ci95_hi": 1.0094, "stdev": 0.0859, "task_count": 22, "weight": 0.15, "format_rate": 1.0, "score_if_valid": 0.9735 }, "regional": { "mean_score": 0.9444, "ci95_lo": 0.8802, "ci95_hi": 1.0087, "stdev": 0.1605, "task_count": 24, "weight": 0.05, "format_rate": 1.0, "score_if_valid": 0.9444 }, "risk": { "mean_score": 0.9, "ci95_lo": 0.7651, "ci95_hi": 1.0349, "stdev": 0.3078, "task_count": 20, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 0.9 }, "safety": { "mean_score": 0.9694, "ci95_lo": 0.9093, "ci95_hi": 1.0294, "stdev": 0.1061, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.9694 }, "sensory": { "mean_score": 0.5974, "ci95_lo": 0.4459, "ci95_hi": 0.7488, "stdev": 0.3541, "task_count": 21, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.5974 }, "structured_output": { "mean_score": 0.8139, "ci95_lo": 0.6699, "ci95_hi": 0.9579, "stdev": 0.3286, "task_count": 20, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.8139 }, "vocabulary": { "mean_score": 0.913, "ci95_lo": 0.8106, "ci95_hi": 1.0155, "stdev": 0.2506, "task_count": 23, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 0.913 } }, "aggregate": { "score": 79.56, "ci95_lo": 75.7, "ci95_hi": 83.41, "scale": "0-100", "partial": false, "missing_categories": [] }, "metrics": { "latency_ms_mean": 889.26, "latency_ms_median": 661.233, "input_tokens_mean": 728.8, "output_tokens_mean": 50.1, "usd_total": 0.180415, "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)." } }