{ "benchmark_version": "0.3.0", "ogs_version": "0.2.0", "run_id": "581f9390-371f-4a10-98a3-6f9b21ac2bdc", "run_at": "2026-04-19T20:50:37.696917+00:00", "model": { "id": "gemini-2.5-pro", "adapter": "gemini", "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", "anthropic": "0.96.0", "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": 418, "output_tokens": 1, "latency_ms": 4067.4, "usd": 0.000532, "model_version": "gemini-2.5-pro", "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": 418, "output_tokens": 1, "latency_ms": 5013.7, "usd": 0.000532, "model_version": "gemini-2.5-pro", "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": 418, "output_tokens": 1, "latency_ms": 4040.2, "usd": 0.000532, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 418.0, "output_tokens_mean": 1.0, "latency_ms_mean": 4373.767, "usd_sum": 0.001596 } }, { "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": 409, "output_tokens": 1, "latency_ms": 4739.6, "usd": 0.000521, "model_version": "gemini-2.5-pro", "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": 409, "output_tokens": 1, "latency_ms": 3775.3, "usd": 0.000521, "model_version": "gemini-2.5-pro", "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": 409, "output_tokens": 1, "latency_ms": 4143.3, "usd": 0.000521, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 409.0, "output_tokens_mean": 1.0, "latency_ms_mean": 4219.4, "usd_sum": 0.001563 } }, { "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": 421, "output_tokens": 1, "latency_ms": 8169.7, "usd": 0.000536, "model_version": "gemini-2.5-pro", "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": 421, "output_tokens": 1, "latency_ms": 11962.5, "usd": 0.000536, "model_version": "gemini-2.5-pro", "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": 421, "output_tokens": 1, "latency_ms": 8605.9, "usd": 0.000536, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 421.0, "output_tokens_mean": 1.0, "latency_ms_mean": 9579.367, "usd_sum": 0.001608 } }, { "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": 443, "output_tokens": 2, "latency_ms": 13439.1, "usd": 0.000574, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 443, "output_tokens": 2, "latency_ms": 8966.8, "usd": 0.000574, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 443, "output_tokens": 2, "latency_ms": 12473.8, "usd": 0.000574, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 443.0, "output_tokens_mean": 2.0, "latency_ms_mean": 11626.567, "usd_sum": 0.001722 } }, { "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": 373, "output_tokens": 4, "latency_ms": 7038.1, "usd": 0.000506, "model_version": "gemini-2.5-pro", "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": 373, "output_tokens": 4, "latency_ms": 6688.4, "usd": 0.000506, "model_version": "gemini-2.5-pro", "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": 373, "output_tokens": 4, "latency_ms": 7887.4, "usd": 0.000506, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 373.0, "output_tokens_mean": 4.0, "latency_ms_mean": 7204.633, "usd_sum": 0.001518 } }, { "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": "[\n \"main_protein\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"seasoning\",\n \"aromatic_garnish\",\n \"textural_element\"\n]", "compliant": true, "score": 0.8333, "detail": { "predicted": [ "aromatic_garnish", "fat_component", "main_protein", "sauce", "seasoning", "starch", "textural_element" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 0.7143, "recall": 1.0 }, "metrics": { "input_tokens": 502, "output_tokens": 51, "latency_ms": 6473.1, "usd": 0.001138, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"main_protein\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"seasoning\",\n \"aromatic_garnish\",\n \"textural_element\"\n]", "compliant": true, "score": 0.8333, "detail": { "predicted": [ "aromatic_garnish", "fat_component", "main_protein", "sauce", "seasoning", "starch", "textural_element" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 0.7143, "recall": 1.0 }, "metrics": { "input_tokens": 502, "output_tokens": 51, "latency_ms": 9987.5, "usd": 0.001138, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"main_protein\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"seasoning\",\n \"textural_element\",\n \"aromatic_garnish\"\n]", "compliant": true, "score": 0.8333, "detail": { "predicted": [ "aromatic_garnish", "fat_component", "main_protein", "sauce", "seasoning", "starch", "textural_element" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 0.7143, "recall": 1.0 }, "metrics": { "input_tokens": 502, "output_tokens": 51, "latency_ms": 7125.9, "usd": 0.001138, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.8333, "score_summary": { "mean": 0.8333, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.8333, "ci95_hi": 0.8333, "n": 3 }, "score_if_valid": 0.8333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 502.0, "output_tokens_mean": 51.0, "latency_ms_mean": 7862.167, "usd_sum": 0.003414 } }, { "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": 324, "output_tokens": 1, "latency_ms": 4488.4, "usd": 0.000415, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 324, "output_tokens": 1, "latency_ms": 4189.5, "usd": 0.000415, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 324, "output_tokens": 1, "latency_ms": 3453.5, "usd": 0.000415, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 4043.8, "usd_sum": 0.001245 } }, { "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": 407, "output_tokens": 1, "latency_ms": 3575.3, "usd": 0.000519, "model_version": "gemini-2.5-pro", "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": 407, "output_tokens": 1, "latency_ms": 3288.1, "usd": 0.000519, "model_version": "gemini-2.5-pro", "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": 407, "output_tokens": 1, "latency_ms": 3153.4, "usd": 0.000519, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 407.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3338.933, "usd_sum": 0.001557 } }, { "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": 408, "output_tokens": 1, "latency_ms": 4522.3, "usd": 0.00052, "model_version": "gemini-2.5-pro", "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": 408, "output_tokens": 1, "latency_ms": 4456.2, "usd": 0.00052, "model_version": "gemini-2.5-pro", "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": 408, "output_tokens": 1, "latency_ms": 5253.8, "usd": 0.00052, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 4744.1, "usd_sum": 0.00156 } }, { "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": "3", "compliant": true, "score": 1.0, "detail": { "predicted": 3.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 404, "output_tokens": 1, "latency_ms": 22032.8, "usd": 0.000515, "model_version": "gemini-2.5-pro", "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": 404, "output_tokens": 1, "latency_ms": 5861.1, "usd": 0.000515, "model_version": "gemini-2.5-pro", "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": 404, "output_tokens": 1, "latency_ms": 6023.7, "usd": 0.000515, "model_version": "gemini-2.5-pro", "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": 404.0, "output_tokens_mean": 1.0, "latency_ms_mean": 11305.867, "usd_sum": 0.001545 } }, { "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": 405, "output_tokens": 1, "latency_ms": 3580.8, "usd": 0.000516, "model_version": "gemini-2.5-pro", "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": 405, "output_tokens": 1, "latency_ms": 4013.6, "usd": 0.000516, "model_version": "gemini-2.5-pro", "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": 405, "output_tokens": 1, "latency_ms": 3535.5, "usd": 0.000516, "model_version": "gemini-2.5-pro", "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": 405.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3709.967, "usd_sum": 0.001548 } }, { "task_id": "ogs:core:benchmark-task:comp-012", "category": "composition", "capability": "reduction_level", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_mae", "context_needs": [ "scales.reduction_level" ], "prompt_template_hash": "fa91f74e86a4cffb", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Reduction level (0-5 integer)\n\n- 0: no reduction (raw stock, unreduced liquid)\n- 1: light simmer reduction (~10%)\n- 2: modest reduction (~30%, nappe forming)\n- 3: substantial reduction (~50%, demi-glace territory)\n- 4: heavy reduction (~75%, glace-like, syrupy)\n- 5: near-complete reduction (glace de viande, paste)\n\n---\n\nUsing the OGS reduction level, return the integer for glace de viande (gelatinous concentrate that sets firmly at room temperature).\n\nINPUT:\n{\n \"description\": \"glace de viande, reduced from 10 L brown stock to ~500 mL\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 5, "tolerance": 0 }, "samples": [ { "sample": 0, "raw_response": "5", "compliant": true, "score": 1.0, "detail": { "predicted": 5.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 403, "output_tokens": 1, "latency_ms": 4973.9, "usd": 0.000514, "model_version": "gemini-2.5-pro", "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": 403, "output_tokens": 1, "latency_ms": 5047.0, "usd": 0.000514, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "5", "compliant": true, "score": 1.0, "detail": { "predicted": 5.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 403, "output_tokens": 1, "latency_ms": 3664.9, "usd": 0.000514, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 403.0, "output_tokens_mean": 1.0, "latency_ms_mean": 4561.933, "usd_sum": 0.001542 } }, { "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": "poached", "compliant": true, "score": 1.0, "detail": { "predicted": "poached", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 418, "output_tokens": 2, "latency_ms": 9513.4, "usd": 0.000543, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "poached", "compliant": true, "score": 1.0, "detail": { "predicted": "poached", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 418, "output_tokens": 2, "latency_ms": 9293.3, "usd": 0.000543, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "poached", "compliant": true, "score": 1.0, "detail": { "predicted": "poached", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 418, "output_tokens": 2, "latency_ms": 7723.4, "usd": 0.000543, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 418.0, "output_tokens_mean": 2.0, "latency_ms_mean": 8843.367, "usd_sum": 0.001629 } }, { "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": 370, "output_tokens": 5, "latency_ms": 8094.3, "usd": 0.000513, "model_version": "gemini-2.5-pro", "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": 370, "output_tokens": 5, "latency_ms": 7453.9, "usd": 0.000513, "model_version": "gemini-2.5-pro", "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": 370, "output_tokens": 5, "latency_ms": 9341.2, "usd": 0.000513, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 8296.467, "usd_sum": 0.001539 } }, { "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": "[\n \"main_protein\",\n \"starch\",\n \"sauce\",\n \"main_vegetable\",\n \"textural_element\",\n \"aromatic_garnish\"\n]", "compliant": true, "score": 0.6154, "detail": { "predicted": [ "aromatic_garnish", "main_protein", "main_vegetable", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.6667, "recall": 0.5714 }, "metrics": { "input_tokens": 341, "output_tokens": 46, "latency_ms": 13606.5, "usd": 0.000886, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"main_protein\",\n \"starch\",\n \"sauce\",\n \"aromatic_garnish\",\n \"textural_element\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "aromatic_garnish", "main_protein", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.8, "recall": 0.5714 }, "metrics": { "input_tokens": 341, "output_tokens": 38, "latency_ms": 14194.3, "usd": 0.000806, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"main_protein\",\n \"starch\",\n \"sauce\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n]", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "acid_component", "aromatic_garnish", "main_protein", "sauce", "seasoning", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.8571, "recall": 0.8571 }, "metrics": { "input_tokens": 341, "output_tokens": 51, "latency_ms": 12644.6, "usd": 0.000936, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.7131, "score_summary": { "mean": 0.7131, "stdev": 0.1273, "sem": 0.0735, "ci95_lo": 0.569, "ci95_hi": 0.8572, "n": 3 }, "score_if_valid": 0.7131, "format_rate": 1.0, "metrics": { "input_tokens_mean": 341.0, "output_tokens_mean": 45.0, "latency_ms_mean": 13481.8, "usd_sum": 0.002628 } }, { "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": 320, "output_tokens": 1, "latency_ms": 3556.6, "usd": 0.00041, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 320, "output_tokens": 1, "latency_ms": 4737.4, "usd": 0.00041, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 320, "output_tokens": 1, "latency_ms": 4712.3, "usd": 0.00041, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 4335.433, "usd_sum": 0.00123 } }, { "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": 423, "output_tokens": 1, "latency_ms": 7681.7, "usd": 0.000539, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 423, "output_tokens": 1, "latency_ms": 6848.5, "usd": 0.000539, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 423, "output_tokens": 1, "latency_ms": 8146.6, "usd": 0.000539, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 423.0, "output_tokens_mean": 1.0, "latency_ms_mean": 7558.933, "usd_sum": 0.001617 } }, { "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": 358, "output_tokens": 3, "latency_ms": 7864.3, "usd": 0.000478, "model_version": "gemini-2.5-pro", "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": 358, "output_tokens": 3, "latency_ms": 6720.2, "usd": 0.000478, "model_version": "gemini-2.5-pro", "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": 358, "output_tokens": 3, "latency_ms": 9433.9, "usd": 0.000478, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 358.0, "output_tokens_mean": 3.0, "latency_ms_mean": 8006.133, "usd_sum": 0.001434 } }, { "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": 324, "output_tokens": 1, "latency_ms": 4965.9, "usd": 0.000415, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 324, "output_tokens": 1, "latency_ms": 5193.2, "usd": 0.000415, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 324, "output_tokens": 1, "latency_ms": 5161.6, "usd": 0.000415, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 5106.9, "usd_sum": 0.001245 } }, { "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": 419, "output_tokens": 1, "latency_ms": 5226.8, "usd": 0.000534, "model_version": "gemini-2.5-pro", "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": 419, "output_tokens": 1, "latency_ms": 4437.9, "usd": 0.000534, "model_version": "gemini-2.5-pro", "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": 419, "output_tokens": 1, "latency_ms": 6446.9, "usd": 0.000534, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 419.0, "output_tokens_mean": 1.0, "latency_ms_mean": 5370.533, "usd_sum": 0.001602 } }, { "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": 932, "output_tokens": 1, "latency_ms": 5342.9, "usd": 0.001175, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 932, "output_tokens": 1, "latency_ms": 5135.9, "usd": 0.001175, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 932, "output_tokens": 1, "latency_ms": 5056.4, "usd": 0.001175, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 932.0, "output_tokens_mean": 1.0, "latency_ms_mean": 5178.4, "usd_sum": 0.003525 } }, { "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": 975, "output_tokens": 4, "latency_ms": 4442.8, "usd": 0.001259, "model_version": "gemini-2.5-pro", "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": 975, "output_tokens": 4, "latency_ms": 5309.8, "usd": 0.001259, "model_version": "gemini-2.5-pro", "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": 975, "output_tokens": 4, "latency_ms": 4332.6, "usd": 0.001259, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 975.0, "output_tokens_mean": 4.0, "latency_ms_mean": 4695.067, "usd_sum": 0.003777 } }, { "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": 925, "output_tokens": 1, "latency_ms": 7958.0, "usd": 0.001166, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 925, "output_tokens": 1, "latency_ms": 6580.0, "usd": 0.001166, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 925, "output_tokens": 1, "latency_ms": 6135.8, "usd": 0.001166, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 925.0, "output_tokens_mean": 1.0, "latency_ms_mean": 6891.267, "usd_sum": 0.003498 } }, { "task_id": "ogs:core:benchmark-task:diet-004", "category": "dietary", "capability": "kosher_meat_dairy", "difficulty": "medium", "cuisine_region": "italian", "scorer": "exact_match", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "85fc94958c4357ef", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nChicken parmigiana is breaded chicken breast topped with tomato sauce and melted mozzarella, served with a side of cream-rich garlic mashed potatoes. From a kosher perspective, what is the core violation? Respond with one short phrase.\n\nINPUT:\n{\n \"dish\": \"chicken parmigiana with creamy mash\"\n}\n\nANSWER FORMAT: exact:string", "expected": { "value": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "samples": [ { "sample": 0, "raw_response": "Mixing meat and dairy", "compliant": true, "score": 1.0, "detail": { "predicted": "mixing meat and dairy", "expected": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "metrics": { "input_tokens": 914, "output_tokens": 4, "latency_ms": 5994.6, "usd": 0.001183, "model_version": "gemini-2.5-pro", "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": 914, "output_tokens": 4, "latency_ms": 7908.3, "usd": 0.001183, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Mixing meat and dairy", "compliant": true, "score": 1.0, "detail": { "predicted": "mixing meat and dairy", "expected": "mixing meat and dairy", "aliases": [ "meat and dairy mixed", "basar b'chalav", "poultry with dairy", "meat with dairy" ] }, "metrics": { "input_tokens": 914, "output_tokens": 4, "latency_ms": 4379.1, "usd": 0.001183, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 914.0, "output_tokens_mean": 4.0, "latency_ms_mean": 6094.0, "usd_sum": 0.003549 } }, { "task_id": "ogs:core:benchmark-task:diet-005", "category": "dietary", "capability": "allergen_detection", "difficulty": "easy", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "f40f4c25a2ee4b71", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nFor a dish of pesto genovese made from basil, garlic, pine nuts, parmesan, pecorino, and olive oil, list the EU Annex II allergens that must be declared. Return a comma-separated list using the OGS allergen IDs.\n\nINPUT:\n{\n \"dish\": \"pesto genovese\",\n \"ingredients\": [\n \"basil\",\n \"garlic\",\n \"pine nuts\",\n \"parmesan\",\n \"pecorino\",\n \"olive oil\"\n ]\n}\n\nANSWER FORMAT: set:comma-separated OGS allergen IDs", "expected": { "values": [ "tree_nuts", "milk" ] }, "samples": [ { "sample": 0, "raw_response": "milk,tree_nuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "milk", "tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 970, "output_tokens": 5, "latency_ms": 6038.9, "usd": 0.001262, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "milk,tree_nuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "milk", "tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 970, "output_tokens": 5, "latency_ms": 7606.7, "usd": 0.001262, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "milk,tree_nuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "milk", "tree_nuts" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 970, "output_tokens": 5, "latency_ms": 5525.2, "usd": 0.001262, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 970.0, "output_tokens_mean": 5.0, "latency_ms_mean": 6390.267, "usd_sum": 0.003786 } }, { "task_id": "ogs:core:benchmark-task:diet-006", "category": "dietary", "capability": "allergen_detection", "difficulty": "medium", "cuisine_region": "thai", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "7f45e388301a68a5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nReturn the EU Annex II allergens that must be declared for a standard pad thai (rice noodles, shrimp, egg, tamarind, fish sauce, palm sugar, roasted peanuts, bean sprouts, garlic chives, lime, chili).\n\nINPUT:\n{\n \"dish\": \"pad thai\"\n}\n\nANSWER FORMAT: set:comma-separated OGS allergen IDs", "expected": { "values": [ "crustaceans", "eggs", "fish", "peanuts" ] }, "samples": [ { "sample": 0, "raw_response": "crustaceans,eggs,fish,peanuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "crustaceans", "eggs", "fish", "peanuts" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 915, "output_tokens": 10, "latency_ms": 8711.8, "usd": 0.001244, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "crustaceans,eggs,fish,peanuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "crustaceans", "eggs", "fish", "peanuts" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 915, "output_tokens": 10, "latency_ms": 8450.0, "usd": 0.001244, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "crustaceans,eggs,fish,peanuts", "compliant": true, "score": 1.0, "detail": { "predicted": [ "crustaceans", "eggs", "fish", "peanuts" ], "expected": [ "crustaceans", "eggs", "fish", "peanuts" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 915, "output_tokens": 10, "latency_ms": 7163.3, "usd": 0.001244, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 915.0, "output_tokens_mean": 10.0, "latency_ms_mean": 8108.367, "usd_sum": 0.003732 } }, { "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": "nutritional yeast", "compliant": true, "score": 0.0, "detail": { "predicted": "nutritional yeast", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 910, "output_tokens": 3, "latency_ms": 51147.5, "usd": 0.001168, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "miso", "compliant": true, "score": 0.0, "detail": { "predicted": "miso", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 910, "output_tokens": 2, "latency_ms": 33539.5, "usd": 0.001158, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cashews", "compliant": true, "score": 0.0, "detail": { "predicted": "cashews", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 910, "output_tokens": 2, "latency_ms": 39864.9, "usd": 0.001158, "model_version": "gemini-2.5-pro", "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": 910.0, "output_tokens_mean": 2.333, "latency_ms_mean": 41517.3, "usd_sum": 0.003484 } }, { "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": "Rice", "compliant": true, "score": 0.0, "detail": { "predicted": "rice", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 898, "output_tokens": 1, "latency_ms": 13572.6, "usd": 0.001133, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Rice", "compliant": true, "score": 0.0, "detail": { "predicted": "rice", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 898, "output_tokens": 1, "latency_ms": 14142.3, "usd": 0.001133, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Rice", "compliant": true, "score": 0.0, "detail": { "predicted": "rice", "expected": "rice flour", "aliases": [ "cornstarch", "corn starch", "cornflour", "tapioca starch", "tapioca flour" ] }, "metrics": { "input_tokens": 898, "output_tokens": 1, "latency_ms": 15462.5, "usd": 0.001133, "model_version": "gemini-2.5-pro", "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": 898.0, "output_tokens_mean": 1.0, "latency_ms_mean": 14392.467, "usd_sum": 0.003399 } }, { "task_id": "ogs:core:benchmark-task:diet-009", "category": "dietary", "capability": "vegan_compatibility", "difficulty": "medium", "cuisine_region": "global", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "936752891554dba3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nFrom this list, return every item that is NOT vegan as a comma-separated list: honey, agave nectar, wine clarified with isinglass, wine clarified with bentonite, carmine, nutritional yeast, shellac, maple syrup, worcestershire sauce (traditional), vegetable glycerin.\n\nINPUT:\n{\n \"items\": [\n \"honey\",\n \"agave nectar\",\n \"wine clarified with isinglass\",\n \"wine clarified with bentonite\",\n \"carmine\",\n \"nutritional yeast\",\n \"shellac\",\n \"maple syrup\",\n \"worcestershire sauce (traditional)\",\n \"vegetable glycerin\"\n ]\n}\n\nANSWER FORMAT: set:comma-separated item names", "expected": { "values": [ "honey", "wine clarified with isinglass", "carmine", "shellac", "worcestershire sauce (traditional)" ] }, "samples": [ { "sample": 0, "raw_response": "honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 1.0, "detail": { "predicted": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1000, "output_tokens": 23, "latency_ms": 5897.1, "usd": 0.00148, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 1.0, "detail": { "predicted": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1000, "output_tokens": 23, "latency_ms": 5931.1, "usd": 0.00148, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "honey,wine clarified with isinglass,carmine,shellac,worcestershire sauce (traditional)", "compliant": true, "score": 1.0, "detail": { "predicted": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "expected": [ "carmine", "honey", "shellac", "wine clarified with isinglass", "worcestershire sauce (traditional)" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1000, "output_tokens": 23, "latency_ms": 6167.8, "usd": 0.00148, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1000.0, "output_tokens_mean": 23.0, "latency_ms_mean": 5998.667, "usd_sum": 0.00444 } }, { "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": "cereals_containing_gluten,eggs,fish,milk,molluscs", "compliant": true, "score": 0.75, "detail": { "predicted": [ "cereals_containing_gluten", "eggs", "fish", "milk", "molluscs" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.6, "recall": 1.0 }, "metrics": { "input_tokens": 947, "output_tokens": 17, "latency_ms": 10037.8, "usd": 0.001354, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "cereals_containing_gluten,molluscs,fish,eggs,milk", "compliant": true, "score": 0.75, "detail": { "predicted": [ "cereals_containing_gluten", "eggs", "fish", "milk", "molluscs" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.6, "recall": 1.0 }, "metrics": { "input_tokens": 947, "output_tokens": 17, "latency_ms": 24525.2, "usd": 0.001354, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cereals_containing_gluten,eggs,fish,milk,molluscs", "compliant": true, "score": 0.75, "detail": { "predicted": [ "cereals_containing_gluten", "eggs", "fish", "milk", "molluscs" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 0.6, "recall": 1.0 }, "metrics": { "input_tokens": 947, "output_tokens": 17, "latency_ms": 13803.4, "usd": 0.001354, "model_version": "gemini-2.5-pro", "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": 947.0, "output_tokens_mean": 17.0, "latency_ms_mean": 16122.133, "usd_sum": 0.004062 } }, { "task_id": "ogs:core:benchmark-task:diet-011", "category": "dietary", "capability": "low_fodmap", "difficulty": "hard", "cuisine_region": "global", "scorer": "set_f1", "context_needs": [ "rules.dietary", "rules.allergens_eu", "vocab.dietary_labels" ], "prompt_template_hash": "bdd7970997c11172", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Dietary labels and rules\n\nCanonical dietary label IDs (lowercase snake_case):\n`vegan`, `vegetarian`, `pescatarian`, `halal`, `kosher`, `gluten_free`, `dairy_free`, `nut_free`, `shellfish_free`, `egg_free`, `soy_free`, `low_fodmap`\n\nHigh-level rules (non-exhaustive):\n- `vegan`: no animal-derived ingredients, including honey, dairy, eggs, gelatine, carmine, isinglass, shellac, animal rennet, or fish sauce.\n- `vegetarian`: no meat, poultry, fish, shellfish, or animal-derived rennet/gelatine. Dairy and eggs permitted.\n- `pescatarian`: no meat or poultry. Fish and shellfish permitted.\n- `halal`: no pork or pork derivatives, no alcohol, meat must be zabihah-slaughtered. Gelatine must be from halal source.\n- `kosher`: no pork or shellfish, no mixing of meat and dairy, meat must be shechita-slaughtered. Separate utensils for meat/dairy.\n- `gluten_free`: no wheat, barley, rye, or derivatives (including malt, soy sauce with wheat, seitan).\n- `dairy_free`: no milk, butter, cream, cheese, whey, casein, ghee, yogurt, or lactose.\n- `nut_free`: no tree nuts (almond, cashew, walnut, hazelnut, pecan, pistachio, macadamia, brazil, pine nut). Peanuts are legumes but are usually treated as a separate allergen.\n- `shellfish_free`: no crustaceans (shrimp, crab, lobster, crayfish) or molluscs (mussel, clam, oyster, scallop, squid, octopus).\n- `low_fodmap`: restrict high-FODMAP ingredients (onion, garlic, wheat, beans, lactose, honey, most stone fruit).\n\nA recipe is compatible with a label if and only if **all** its ingredients comply with the label's rules.\n\n### EU 14 declarable allergens (Regulation 1169/2011 Annex II)\n\n- `cereals_containing_gluten`\n- `crustaceans`\n- `eggs`\n- `fish`\n- `peanuts`\n- `soybeans`\n- `milk`\n- `tree_nuts`\n- `celery`\n- `mustard`\n- `sesame`\n- `sulphur_dioxide`\n- `lupin`\n- `molluscs`\n\nUse exactly these IDs when declaring allergens in OGS documents.\n\n### Dietary labels\n\nvegan, vegetarian, pescatarian, halal, kosher, gluten_free, dairy_free, nut_free, shellfish_free, egg_free, soy_free, low_fodmap\n\n---\n\nReturn the low-FODMAP violations in this dish as a comma-separated list of ingredient names: garlic-infused olive oil, white onion, lactose-free milk, wheat pasta, lean chicken, fresh chives, honey, aged parmesan.\n\nINPUT:\n{\n \"ingredients\": [\n \"garlic-infused olive oil\",\n \"white onion\",\n \"lactose-free milk\",\n \"wheat pasta\",\n \"lean chicken\",\n \"fresh chives\",\n \"honey\",\n \"aged parmesan\"\n ]\n}\n\nANSWER FORMAT: set:comma-separated ingredient names", "expected": { "values": [ "white onion", "wheat pasta", "honey" ] }, "samples": [ { "sample": 0, "raw_response": "white onion,wheat pasta,honey", "compliant": true, "score": 1.0, "detail": { "predicted": [ "honey", "wheat pasta", "white onion" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 972, "output_tokens": 7, "latency_ms": 6768.4, "usd": 0.001285, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "white onion,wheat pasta,honey", "compliant": true, "score": 1.0, "detail": { "predicted": [ "honey", "wheat pasta", "white onion" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 972, "output_tokens": 7, "latency_ms": 7399.3, "usd": 0.001285, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "white onion,wheat pasta,honey", "compliant": true, "score": 1.0, "detail": { "predicted": [ "honey", "wheat pasta", "white onion" ], "expected": [ "honey", "wheat pasta", "white onion" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 972, "output_tokens": 7, "latency_ms": 7196.2, "usd": 0.001285, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 972.0, "output_tokens_mean": 7.0, "latency_ms_mean": 7121.3, "usd_sum": 0.003855 } }, { "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": 922, "output_tokens": 3, "latency_ms": 5278.1, "usd": 0.001183, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "pescatarian", "compliant": true, "score": 1.0, "detail": { "predicted": [ "pescatarian" ], "expected": [ "pescatarian" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 922, "output_tokens": 3, "latency_ms": 3926.3, "usd": 0.001183, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "pescatarian", "compliant": true, "score": 1.0, "detail": { "predicted": [ "pescatarian" ], "expected": [ "pescatarian" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 922, "output_tokens": 3, "latency_ms": 3688.4, "usd": 0.001183, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 922.0, "output_tokens_mean": 3.0, "latency_ms_mean": 4297.6, "usd_sum": 0.003549 } }, { "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": 514, "output_tokens": 1, "latency_ms": 3099.8, "usd": 0.000652, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 514, "output_tokens": 1, "latency_ms": 2945.7, "usd": 0.000652, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 514, "output_tokens": 1, "latency_ms": 3438.9, "usd": 0.000652, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 514.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3161.467, "usd_sum": 0.001956 } }, { "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": 496, "output_tokens": 3, "latency_ms": 2967.9, "usd": 0.00065, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 496, "output_tokens": 3, "latency_ms": 3505.7, "usd": 0.00065, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 496, "output_tokens": 3, "latency_ms": 3380.9, "usd": 0.00065, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 3.0, "latency_ms_mean": 3284.833, "usd_sum": 0.00195 } }, { "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": 493, "output_tokens": 1, "latency_ms": 2710.2, "usd": 0.000626, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 493, "output_tokens": 1, "latency_ms": 3508.5, "usd": 0.000626, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 493, "output_tokens": 1, "latency_ms": 3246.3, "usd": 0.000626, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 493.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3155.0, "usd_sum": 0.001878 } }, { "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": 497, "output_tokens": 1, "latency_ms": 2724.9, "usd": 0.000631, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 497, "output_tokens": 1, "latency_ms": 2687.2, "usd": 0.000631, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 497, "output_tokens": 1, "latency_ms": 2475.8, "usd": 0.000631, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 497.0, "output_tokens_mean": 1.0, "latency_ms_mean": 2629.3, "usd_sum": 0.001893 } }, { "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": 514, "output_tokens": 2, "latency_ms": 2589.0, "usd": 0.000663, "model_version": "gemini-2.5-pro", "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": 514, "output_tokens": 2, "latency_ms": 3266.1, "usd": 0.000663, "model_version": "gemini-2.5-pro", "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": 514, "output_tokens": 2, "latency_ms": 3135.6, "usd": 0.000663, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 514.0, "output_tokens_mean": 2.0, "latency_ms_mean": 2996.9, "usd_sum": 0.001989 } }, { "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": 517, "output_tokens": 5, "latency_ms": 2224.9, "usd": 0.000696, "model_version": "gemini-2.5-pro", "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": 517, "output_tokens": 5, "latency_ms": 2628.0, "usd": 0.000696, "model_version": "gemini-2.5-pro", "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": 517, "output_tokens": 5, "latency_ms": 2263.6, "usd": 0.000696, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 517.0, "output_tokens_mean": 5.0, "latency_ms_mean": 2372.167, "usd_sum": 0.002088 } }, { "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": 729, "output_tokens": 1, "latency_ms": 25724.2, "usd": 0.000921, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 729, "output_tokens": 1, "latency_ms": 19476.1, "usd": 0.000921, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 729, "output_tokens": 1, "latency_ms": 14681.8, "usd": 0.000921, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 729.0, "output_tokens_mean": 1.0, "latency_ms_mean": 19960.7, "usd_sum": 0.002763 } }, { "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": 516, "output_tokens": 5, "latency_ms": 3551.3, "usd": 0.000695, "model_version": "gemini-2.5-pro", "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": 516, "output_tokens": 5, "latency_ms": 4656.6, "usd": 0.000695, "model_version": "gemini-2.5-pro", "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": 516, "output_tokens": 5, "latency_ms": 3668.1, "usd": 0.000695, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 516.0, "output_tokens_mean": 5.0, "latency_ms_mean": 3958.667, "usd_sum": 0.002085 } }, { "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's primary weakness is its structural and flavor monotony. Four of the five courses rely on a puréed or creamy, soft-textured base (velouté, risotto, pumpkin purée, sweet potato purée, cheesecake), creating a repetitive and heavy dining experience. This is compounded by an over-reliance on a very narrow, sweet-and-earthy flavor profile dominated by pumpkin and related squashes across the amuse, appetizer, fish, and dessert courses. A second significant weakness is its failure to meet the specified dietary constraints, as the standard menu path is not nut-free due to the amaretti crumble (almonds) and pecan brittle (pecans), requiring modifications that could compromise the intended texture of those dishes.\n\nTo address these issues, I suggest replacing the fish course, \"pan-seared scallops, pumpkin purée, crispy pancetta,\" with a new dish: \"Seared Cod with a Warm Salad of Puy Lentils, Roasted Fennel, and a Caper-Brown Butter Vinaigrette.\" This change is specific and targets the core problems of the menu's flow and textural repetition. It remains seasonally appropriate while introducing a completely different structure and set of flavors between the appetizer and main courses.\n\nThis single change rectifies the identified weaknesses in several ways. First, it breaks the relentless chain of purées by introducing the firm texture of lentils and the light anise of roasted fennel, providing much-needed structural contrast. Second, the briny capers and bright acidity in the vinaigrette cut through the richness of the preceding risotto and effectively cleanse the palate for the pork loin. Finally, this proposed dish is inherently nut-free, helping to create a more robust and compliant menu path without requiring last-minute omissions that diminish the guest experience.", "compliant": true, "score": 1.0, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies two major weaknesses: repeated pumpkin/squash flavor monotony and consecutive creamy/purée-heavy textures, plus the nut-allergen issue." }, { "id": "remediation", "weight": 0.3, "score": 1.0, "note": "It proposes a concrete, seasonally plausible replacement dish with named ingredients and technique that directly breaks the monotony and improves flow." }, { "id": "justification", "weight": 0.3, "score": 1.0, "note": "The reasoning is mechanism-based, citing structural contrast, palate-cleansing acidity, and nut-free pathway compliance rather than generic praise." } ], "summary": "The candidate follows the required three-paragraph free-text format and delivers a focused critique without generic praise. It diagnoses multiple defensible menu flaws, offers a specific replacement, and justifies the change using flow, texture, acidity, and allergen logic.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1304, "output_tokens": 362, "latency_ms": 19442.8, "usd": 0.00525, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "The menu's primary weakness is its profound structural and thematic monotony. Four of the five courses rely heavily on the sweet, earthy notes and soft, puréed textures of pumpkin, butternut squash, or sweet potato. This repetition, from the opening velouté through the risotto, scallop purée, and even the dessert, creates a one-dimensional dining experience that will quickly lead to palate fatigue. The menu lacks crucial contrasting elements like acidity, bitterness, or fresh, crisp textures to reset the palate between the rich, creamy courses.\n\nA second significant flaw is the menu's failure to provide a viable path for the required dietary constraints. For a vegetarian diner, the menu effectively stops after the appetizer, offering no substitution for the fish or main course, which is not a \"viable path.\" Similarly, for a nut-free guest, both the appetizer (amaretti) and dessert (pecan brittle) require modification, indicating that the constraint was an afterthought rather than integrated into the menu's design. This presents a considerable operational and guest experience challenge.\n\nTo address these issues, I suggest replacing the Butternut Squash Risotto appetizer. This course is particularly redundant, following a creamy velouté with another rich, soft, squash-based dish. A better alternative would be a crisp salad of shaved persimmon and radicchio with a sharp vinaigrette and toasted pumpkin seeds. This change introduces bitterness from the radicchio and bright acidity from the vinaigrette to cut through the richness of the surrounding courses, adds a much-needed crisp texture, maintains seasonality, and is inherently vegetarian and easily made nut-free.", "compliant": true, "score": 0.97, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies multiple concrete weaknesses: repeated pumpkin/squash monotony, soft starch-heavy texture repetition, and failure of vegetarian and nut-free paths." }, { "id": "remediation", "weight": 0.3, "score": 1.0, "note": "It proposes a specific seasonal replacement—shaved persimmon and radicchio salad with sharp vinaigrette and toasted pumpkin seeds—that directly breaks the monotony and improves dietary viability." }, { "id": "justification", "weight": 0.3, "score": 0.9, "note": "The reasoning is mechanism-based, citing palate fatigue, lack of acidity/bitterness/crisp texture, and operational issues around dietary constraints, though it does not discuss food-cost math." } ], "summary": "The candidate follows the required three-paragraph free-text format and avoids generic praise. It diagnoses several major menu flaws and offers a concrete, seasonally plausible fix with sound structural justification grounded in balance, contrast, and guest-path viability.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1304, "output_tokens": 327, "latency_ms": 19239.1, "usd": 0.0049, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "The menu's primary weakness is its significant structural and flavour monotony. Four of the five courses rely heavily on a sweet, smooth purée (pumpkin, butternut squash, sweet potato), which will lead to palate fatigue. This repetition of a single texture and a narrow, sweet-leaning flavour profile makes the progression feel one-dimensional. A secondary weakness is the challenge posed to the dietary constraints; key textural elements in two courses (amaretti crumble, pecan brittle) are nut-based, making the nut-free path a compromised, subtractive experience rather than an equally considered alternative.\n\nTo address this, I suggest replacing the fish course, \"pan-seared scallops, pumpkin purée, crispy pancetta,\" with \"pan-seared scallops with a warm, braised lentil and celery root salad, finished with brown butter and parsley.\" This change deliberately introduces a new texture—the slight bite of the lentils and the tender dice of the root vegetable—breaking the relentless chain of purées. It also offers a more earthy, savoury counterpoint to the sweetness of the preceding risotto and subsequent main course.\n\nThis substitution improves the menu flow by providing much-needed textural and flavour contrast. The earthiness of the lentils and celery root, brightened with parsley, acts as a bridge between the rich appetizer and the hearty main, cleansing the palate rather than overwhelming it with more sweetness. This change also strengthens the menu's dietary flexibility; the new fish course is naturally nut-free, and its core lentil and vegetable base can be easily adapted to serve as a standalone, compelling vegetarian main course, far more successfully than the original pork-centric dish could be.", "compliant": true, "score": 0.97, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies two major concrete weaknesses: repeated squash/purée-driven monotony and nut-allergen problems from amaretti and pecans." }, { "id": "remediation", "weight": 0.3, "score": 1.0, "note": "It proposes a specific replacement for the fish course with named ingredients and technique that directly breaks the puree/sweetness pattern." }, { "id": "justification", "weight": 0.3, "score": 0.9, "note": "The reasoning is mechanism-based around palate fatigue, texture contrast, flow, and dietary flexibility, though it is lighter on explicit cross-contact or cost math." } ], "summary": "The answer follows the requested three-paragraph free-text format and avoids generic praise. It diagnoses key menu flaws and offers a concrete, seasonally plausible substitution with solid service-flow and structural-balance justification.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 1304, "output_tokens": 338, "latency_ms": 21515.7, "usd": 0.00501, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.98, "score_summary": { "mean": 0.98, "stdev": 0.0173, "sem": 0.01, "ci95_lo": 0.9604, "ci95_hi": 0.9996, "n": 3 }, "score_if_valid": 0.98, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1304.0, "output_tokens_mean": 342.333, "latency_ms_mean": 20065.867, "usd_sum": 0.01516 } }, { "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": 352, "output_tokens": 1, "latency_ms": 10352.6, "usd": 0.00045, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 352, "output_tokens": 1, "latency_ms": 3844.0, "usd": 0.00045, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 352, "output_tokens": 1, "latency_ms": 7890.3, "usd": 0.00045, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 352.0, "output_tokens_mean": 1.0, "latency_ms_mean": 7362.3, "usd_sum": 0.00135 } }, { "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": 270, "output_tokens": 2, "latency_ms": 2794.5, "usd": 0.000358, "model_version": "gemini-2.5-pro", "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": 270, "output_tokens": 2, "latency_ms": 8456.9, "usd": 0.000358, "model_version": "gemini-2.5-pro", "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": 270, "output_tokens": 2, "latency_ms": 2451.7, "usd": 0.000358, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 270.0, "output_tokens_mean": 2.0, "latency_ms_mean": 4567.7, "usd_sum": 0.001074 } }, { "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": 274, "output_tokens": 2, "latency_ms": 4104.1, "usd": 0.000362, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 274, "output_tokens": 2, "latency_ms": 2357.7, "usd": 0.000362, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 274, "output_tokens": 2, "latency_ms": 3113.7, "usd": 0.000362, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 274.0, "output_tokens_mean": 2.0, "latency_ms_mean": 3191.833, "usd_sum": 0.001086 } }, { "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": 404, "output_tokens": 1, "latency_ms": 8575.7, "usd": 0.000515, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 404, "output_tokens": 1, "latency_ms": 8683.5, "usd": 0.000515, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 404, "output_tokens": 1, "latency_ms": 7163.3, "usd": 0.000515, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 404.0, "output_tokens_mean": 1.0, "latency_ms_mean": 8140.833, "usd_sum": 0.001545 } }, { "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": 272, "output_tokens": 3, "latency_ms": 8518.0, "usd": 0.00037, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 272, "output_tokens": 3, "latency_ms": 4526.6, "usd": 0.00037, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 272, "output_tokens": 3, "latency_ms": 13251.1, "usd": 0.00037, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 272.0, "output_tokens_mean": 3.0, "latency_ms_mean": 8765.233, "usd_sum": 0.00111 } }, { "task_id": "ogs:core:benchmark-task:ml-fr-002", "category": "sensory", "capability": "basic_tastes_profile", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "96a07aeab44536ab", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nPour une sauce beurre blanc classique, donnez le profil sur l'échelle OGS des cinq saveurs [sweet, sour, salty, bitter, umami] sous la forme d'un tableau JSON de cinq nombres entre 0 et 10.\n\nINPUT:\n{\n \"dish\": \"sauce beurre blanc classique\"\n}\n\nANSWER FORMAT: json:array of 5 numbers", "expected": { "values": [ 1, 5, 4, 1, 3 ] }, "samples": [ { "sample": 0, "raw_response": "[1.5, 7.5, 5.0, 0.5, 2.0]", "compliant": true, "score": 0.4, "detail": { "per_position": [ { "index": 0, "predicted": 1.5, "expected": 1, "score": 0.6667 }, { "index": 1, "predicted": 7.5, "expected": 5, "score": 0.0 }, { "index": 2, "predicted": 5.0, "expected": 4, "score": 0.3333 }, { "index": 3, "predicted": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 2.0, "expected": 3, "score": 0.3333 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 389, "output_tokens": 25, "latency_ms": 12034.8, "usd": 0.000736, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[2.5, 7.5, 4.5, 0.5, 3.0]", "compliant": true, "score": 0.4667, "detail": { "per_position": [ { "index": 0, "predicted": 2.5, "expected": 1, "score": 0.0 }, { "index": 1, "predicted": 7.5, "expected": 5, "score": 0.0 }, { "index": 2, "predicted": 4.5, "expected": 4, "score": 0.6667 }, { "index": 3, "predicted": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 3.0, "expected": 3, "score": 1.0 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 389, "output_tokens": 25, "latency_ms": 12914.4, "usd": 0.000736, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[2.5, 7.5, 4.0, 0.5, 3.0]", "compliant": true, "score": 0.5333, "detail": { "per_position": [ { "index": 0, "predicted": 2.5, "expected": 1, "score": 0.0 }, { "index": 1, "predicted": 7.5, "expected": 5, "score": 0.0 }, { "index": 2, "predicted": 4.0, "expected": 4, "score": 1.0 }, { "index": 3, "predicted": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 3.0, "expected": 3, "score": 1.0 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 389, "output_tokens": 25, "latency_ms": 9983.0, "usd": 0.000736, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.4667, "score_summary": { "mean": 0.4667, "stdev": 0.0667, "sem": 0.0385, "ci95_lo": 0.3912, "ci95_hi": 0.5421, "n": 3 }, "score_if_valid": 0.4667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 389.0, "output_tokens_mean": 25.0, "latency_ms_mean": 11644.067, "usd_sum": 0.002208 } }, { "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": 274, "output_tokens": 3, "latency_ms": 3712.5, "usd": 0.000373, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 274, "output_tokens": 3, "latency_ms": 4557.1, "usd": 0.000373, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 274, "output_tokens": 3, "latency_ms": 4186.2, "usd": 0.000373, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 274.0, "output_tokens_mean": 3.0, "latency_ms_mean": 4151.933, "usd_sum": 0.001119 } }, { "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": 338, "output_tokens": 2, "latency_ms": 10785.1, "usd": 0.000443, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 338, "output_tokens": 2, "latency_ms": 16955.8, "usd": 0.000443, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 338, "output_tokens": 2, "latency_ms": 16503.5, "usd": 0.000443, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 2.0, "latency_ms_mean": 14748.133, "usd_sum": 0.001329 } }, { "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": 1, "latency_ms": 5721.2, "usd": 0.000425, "model_version": "gemini-2.5-pro", "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": 1, "latency_ms": 5345.1, "usd": 0.000425, "model_version": "gemini-2.5-pro", "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": 1, "latency_ms": 5313.4, "usd": 0.000425, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 5459.9, "usd_sum": 0.001275 } }, { "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": 340, "output_tokens": 2, "latency_ms": 10913.8, "usd": 0.000445, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 340, "output_tokens": 2, "latency_ms": 11202.9, "usd": 0.000445, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 340, "output_tokens": 2, "latency_ms": 12981.0, "usd": 0.000445, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 340.0, "output_tokens_mean": 2.0, "latency_ms_mean": 11699.233, "usd_sum": 0.001335 } }, { "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": "375", "compliant": true, "score": 1.0, "detail": { "predicted": 375.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 905, "output_tokens": 3, "latency_ms": 4233.5, "usd": 0.001161, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "375", "compliant": true, "score": 1.0, "detail": { "predicted": 375.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 905, "output_tokens": 3, "latency_ms": 4077.6, "usd": 0.001161, "model_version": "gemini-2.5-pro", "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": 905, "output_tokens": 3, "latency_ms": 3903.2, "usd": 0.001161, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 905.0, "output_tokens_mean": 3.0, "latency_ms_mean": 4071.433, "usd_sum": 0.003483 } }, { "task_id": "ogs:core:benchmark-task:nut-002", "category": "nutrition", "capability": "energy_calculation", "difficulty": "easy", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "4b141daaadd9af57", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA 150 mL glass of red wine contains approximately 14 g alcohol, 4 g carbohydrate, no protein, no fat. Return energy in kcal as a single integer.\n\nINPUT:\n{\n \"carb_g\": 4,\n \"protein_g\": 0,\n \"fat_g\": 0,\n \"alcohol_g\": 14\n}\n\nANSWER FORMAT: numeric:integer kcal", "expected": { "value": 114, "tolerance": 5 }, "samples": [ { "sample": 0, "raw_response": "114", "compliant": true, "score": 1.0, "detail": { "predicted": 114.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 912, "output_tokens": 3, "latency_ms": 3945.1, "usd": 0.00117, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "114", "compliant": true, "score": 1.0, "detail": { "predicted": 114.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 912, "output_tokens": 3, "latency_ms": 4863.7, "usd": 0.00117, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "114", "compliant": true, "score": 1.0, "detail": { "predicted": 114.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 912, "output_tokens": 3, "latency_ms": 4759.3, "usd": 0.00117, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 912.0, "output_tokens_mean": 3.0, "latency_ms_mean": 4522.7, "usd_sum": 0.00351 } }, { "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": "668", "compliant": true, "score": 1.0, "detail": { "predicted": 668.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 917, "output_tokens": 3, "latency_ms": 8348.5, "usd": 0.001176, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "668", "compliant": true, "score": 1.0, "detail": { "predicted": 668.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 917, "output_tokens": 3, "latency_ms": 6564.7, "usd": 0.001176, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "668", "compliant": true, "score": 1.0, "detail": { "predicted": 668.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 917, "output_tokens": 3, "latency_ms": 3426.9, "usd": 0.001176, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 917.0, "output_tokens_mean": 3.0, "latency_ms_mean": 6113.367, "usd_sum": 0.003528 } }, { "task_id": "ogs:core:benchmark-task:nut-004", "category": "nutrition", "capability": "protein_estimate", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "42947503c82b308d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nEstimate the protein (g) in a 180 g cooked portion of skinless chicken-breast filet assuming 30% cooking mass loss. Respond with one integer.\n\nINPUT:\n{\n \"raw_mass_g_target_cooked\": 180,\n \"cooking_loss\": 0.3\n}\n\nANSWER FORMAT: numeric:integer g", "expected": { "value": 59, "tolerance": 4 }, "samples": [ { "sample": 0, "raw_response": "59", "compliant": true, "score": 1.0, "detail": { "predicted": 59.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 899, "output_tokens": 2, "latency_ms": 7156.2, "usd": 0.001144, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "59", "compliant": true, "score": 1.0, "detail": { "predicted": 59.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 899, "output_tokens": 2, "latency_ms": 6331.6, "usd": 0.001144, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "59", "compliant": true, "score": 1.0, "detail": { "predicted": 59.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 899, "output_tokens": 2, "latency_ms": 7729.9, "usd": 0.001144, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 899.0, "output_tokens_mean": 2.0, "latency_ms_mean": 7072.567, "usd_sum": 0.003432 } }, { "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": "[64.24, 16.39, 13.725, 446]", "compliant": true, "score": 0.9854, "detail": { "per_position": [ { "index": 0, "predicted": 64.24, "expected": 64.3, "score": 0.98 }, { "index": 1, "predicted": 16.39, "expected": 16.3, "score": 0.97 }, { "index": 2, "predicted": 13.725, "expected": 13.7, "score": 0.9917 }, { "index": 3, "predicted": 446, "expected": 446, "score": 1.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 990, "output_tokens": 27, "latency_ms": 10657.8, "usd": 0.001508, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[64.24, 16.39, 13.725, 446]", "compliant": true, "score": 0.9854, "detail": { "per_position": [ { "index": 0, "predicted": 64.24, "expected": 64.3, "score": 0.98 }, { "index": 1, "predicted": 16.39, "expected": 16.3, "score": 0.97 }, { "index": 2, "predicted": 13.725, "expected": 13.7, "score": 0.9917 }, { "index": 3, "predicted": 446, "expected": 446, "score": 1.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 990, "output_tokens": 27, "latency_ms": 10412.4, "usd": 0.001508, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[64.24, 16.39, 13.725, 446]", "compliant": true, "score": 0.9854, "detail": { "per_position": [ { "index": 0, "predicted": 64.24, "expected": 64.3, "score": 0.98 }, { "index": 1, "predicted": 16.39, "expected": 16.3, "score": 0.97 }, { "index": 2, "predicted": 13.725, "expected": 13.7, "score": 0.9917 }, { "index": 3, "predicted": 446, "expected": 446, "score": 1.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 990, "output_tokens": 27, "latency_ms": 16840.6, "usd": 0.001508, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.9854, "score_summary": { "mean": 0.9854, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.9854, "ci95_hi": 0.9854, "n": 3 }, "score_if_valid": 0.9854, "format_rate": 1.0, "metrics": { "input_tokens_mean": 990.0, "output_tokens_mean": 27.0, "latency_ms_mean": 12636.933, "usd_sum": 0.004524 } }, { "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": "113", "compliant": true, "score": 0.6667, "detail": { "predicted": 113.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 896, "output_tokens": 3, "latency_ms": 5075.7, "usd": 0.00115, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "115", "compliant": true, "score": 0.3333, "detail": { "predicted": 115.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 896, "output_tokens": 3, "latency_ms": 5489.7, "usd": 0.00115, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "113", "compliant": true, "score": 0.6667, "detail": { "predicted": 113.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 896, "output_tokens": 3, "latency_ms": 8501.5, "usd": 0.00115, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.5556, "score_summary": { "mean": 0.5556, "stdev": 0.1925, "sem": 0.1111, "ci95_lo": 0.3377, "ci95_hi": 0.7734, "n": 3 }, "score_if_valid": 0.5556, "format_rate": 1.0, "metrics": { "input_tokens_mean": 896.0, "output_tokens_mean": 3.0, "latency_ms_mean": 6355.633, "usd_sum": 0.00345 } }, { "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": 851, "output_tokens": 1, "latency_ms": 4125.1, "usd": 0.001074, "model_version": "gemini-2.5-pro", "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": 851, "output_tokens": 1, "latency_ms": 3063.0, "usd": 0.001074, "model_version": "gemini-2.5-pro", "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": 851, "output_tokens": 1, "latency_ms": 4511.5, "usd": 0.001074, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 851.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3899.867, "usd_sum": 0.003222 } }, { "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": 867, "output_tokens": 4, "latency_ms": 23369.4, "usd": 0.001124, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "1050", "compliant": true, "score": 0.6, "detail": { "predicted": 1050.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 867, "output_tokens": 4, "latency_ms": 22891.1, "usd": 0.001124, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "1063", "compliant": true, "score": 0.0, "detail": { "predicted": 1063.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 867, "output_tokens": 4, "latency_ms": 28517.6, "usd": 0.001124, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.5333, "score_summary": { "mean": 0.5333, "stdev": 0.5033, "sem": 0.2906, "ci95_lo": -0.0362, "ci95_hi": 1.1029, "n": 3 }, "score_if_valid": 0.5333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 867.0, "output_tokens_mean": 4.0, "latency_ms_mean": 24926.033, "usd_sum": 0.003372 } }, { "task_id": "ogs:core:benchmark-task:nut-009", "category": "nutrition", "capability": "macro_vector", "difficulty": "hard", "cuisine_region": "italian", "scorer": "numeric_vector_mae", "context_needs": [ "rules.nutrition" ], "prompt_template_hash": "641416c8b33c6dbc", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS nutrition reference (per-100 g macro densities)\n\nMacronutrient energy values (EU Regulation 1169/2011 Annex XIV):\n- carbohydrate: **4 kcal/g** (17 kJ/g)\n- protein: **4 kcal/g** (17 kJ/g)\n- fat: **9 kcal/g** (37 kJ/g)\n- alcohol: **7 kcal/g** (29 kJ/g)\n- fibre: **2 kcal/g** (8 kJ/g)\n\nExpress nutrition values per 100 g of the finished component unless explicitly stated otherwise. Round kcal to the nearest integer.\n\nCommon ingredient macros (per 100 g, approximate, for reasoning only):\n- olive oil: 0 C / 0 P / 100 F → 884 kcal\n- butter: 0.1 C / 0.9 P / 81 F → 717 kcal\n- chicken breast (raw, skinless): 0 C / 23 P / 1.2 F → 110 kcal\n- salmon (raw, Atlantic): 0 C / 20 P / 13 F → 208 kcal\n- dry pasta: 75 C / 13 P / 1.5 F → 371 kcal\n- cooked white rice: 28 C / 2.7 P / 0.3 F → 130 kcal\n- granulated sugar: 100 C / 0 P / 0 F → 387 kcal\n- all-purpose flour: 76 C / 10 P / 1 F → 364 kcal\n- whole milk: 4.8 C / 3.4 P / 3.3 F → 61 kcal\n- heavy cream (36%): 2.8 C / 2 P / 37 F → 345 kcal\n- eggs (whole, raw): 1.1 C / 12.6 P / 9.5 F → 143 kcal\n- parmesan: 3.2 C / 35 P / 29 F → 420 kcal\n- tomato (raw): 3.9 C / 0.9 P / 0.2 F → 18 kcal\n- onion (raw): 9 C / 1.1 P / 0.1 F → 40 kcal\n\nWhen summing nutrition across a recipe, scale each ingredient by its mass in grams, then divide by total finished mass to get per-100 g values. Assume no mass loss from evaporation unless the task says otherwise.\n\n---\n\nA simple Alfredo sauce is 100 g butter + 150 g heavy cream (36% fat: 2.8 C / 2 P / 37 F) + 60 g parmesan (3.2 C / 35 P / 29 F), reduced to 250 g finished weight. Return [carb_per100g, protein_per100g, fat_per100g, kcal_per100g] as a JSON array of four numbers.\n\nINPUT:\n{\n \"butter_g\": 100,\n \"cream_g\": 150,\n \"parmesan_g\": 60,\n \"finished_g\": 250\n}\n\nANSWER FORMAT: json:array [carb, protein, fat, kcal] per 100 g", "expected": { "values": [ 2.5, 9.6, 55.2, 545 ] }, "samples": [ { "sample": 0, "raw_response": "[2.488, 9.96, 61.56, 604]", "compliant": true, "score": 0.4767, "detail": { "per_position": [ { "index": 0, "predicted": 2.488, "expected": 2.5, "score": 0.997 }, { "index": 1, "predicted": 9.96, "expected": 9.6, "score": 0.91 }, { "index": 2, "predicted": 61.56, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 604, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 1010, "output_tokens": 25, "latency_ms": 11566.9, "usd": 0.001512, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[2.488, 9.96, 61.56, 604]", "compliant": true, "score": 0.4767, "detail": { "per_position": [ { "index": 0, "predicted": 2.488, "expected": 2.5, "score": 0.997 }, { "index": 1, "predicted": 9.96, "expected": 9.6, "score": 0.91 }, { "index": 2, "predicted": 61.56, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 604, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 1010, "output_tokens": 25, "latency_ms": 12862.4, "usd": 0.001512, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[2.488, 9.96, 61.56, 604]", "compliant": true, "score": 0.4767, "detail": { "per_position": [ { "index": 0, "predicted": 2.488, "expected": 2.5, "score": 0.997 }, { "index": 1, "predicted": 9.96, "expected": 9.6, "score": 0.91 }, { "index": 2, "predicted": 61.56, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 604, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 1010, "output_tokens": 25, "latency_ms": 16266.9, "usd": 0.001512, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.4767, "score_summary": { "mean": 0.4767, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.4767, "ci95_hi": 0.4767, "n": 3 }, "score_if_valid": 0.4767, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1010.0, "output_tokens_mean": 25.0, "latency_ms_mean": 13565.4, "usd_sum": 0.004536 } }, { "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": 897, "output_tokens": 2, "latency_ms": 4174.3, "usd": 0.001141, "model_version": "gemini-2.5-pro", "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": 897, "output_tokens": 2, "latency_ms": 4301.7, "usd": 0.001141, "model_version": "gemini-2.5-pro", "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": 897, "output_tokens": 2, "latency_ms": 6321.6, "usd": 0.001141, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 897.0, "output_tokens_mean": 2.0, "latency_ms_mean": 4932.533, "usd_sum": 0.003423 } }, { "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": 400, "output_tokens": 1, "latency_ms": 13184.1, "usd": 0.00051, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 400, "output_tokens": 1, "latency_ms": 12558.1, "usd": 0.00051, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 400, "output_tokens": 1, "latency_ms": 12752.3, "usd": 0.00051, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 400.0, "output_tokens_mean": 1.0, "latency_ms_mean": 12831.5, "usd_sum": 0.00153 } }, { "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": 384, "output_tokens": 1, "latency_ms": 14329.6, "usd": 0.00049, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 11065.4, "usd": 0.00049, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 11192.0, "usd": 0.00049, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 384.0, "output_tokens_mean": 1.0, "latency_ms_mean": 12195.667, "usd_sum": 0.00147 } }, { "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": 397, "output_tokens": 1, "latency_ms": 10871.2, "usd": 0.000506, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 397, "output_tokens": 1, "latency_ms": 15311.3, "usd": 0.000506, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 397, "output_tokens": 1, "latency_ms": 10579.8, "usd": 0.000506, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 12254.1, "usd_sum": 0.001518 } }, { "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": 368, "output_tokens": 1, "latency_ms": 10093.5, "usd": 0.00047, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 368, "output_tokens": 1, "latency_ms": 13063.5, "usd": 0.00047, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 368, "output_tokens": 1, "latency_ms": 11704.8, "usd": 0.00047, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 368.0, "output_tokens_mean": 1.0, "latency_ms_mean": 11620.6, "usd_sum": 0.00141 } }, { "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": 372, "output_tokens": 1, "latency_ms": 12069.8, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 372, "output_tokens": 1, "latency_ms": 9957.5, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 372, "output_tokens": 1, "latency_ms": 11263.4, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 372.0, "output_tokens_mean": 1.0, "latency_ms_mean": 11096.9, "usd_sum": 0.001425 } }, { "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": 390, "output_tokens": 1, "latency_ms": 14064.2, "usd": 0.000498, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 390, "output_tokens": 1, "latency_ms": 13685.4, "usd": 0.000498, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 390, "output_tokens": 1, "latency_ms": 16691.6, "usd": 0.000498, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 390.0, "output_tokens_mean": 1.0, "latency_ms_mean": 14813.733, "usd_sum": 0.001494 } }, { "task_id": "ogs:core:benchmark-task:pair-007", "category": "pairing", "capability": "regional_pairing", "difficulty": "hard", "cuisine_region": "spanish", "scorer": "ranked_selection", "context_needs": [ "vocab.match_types" ], "prompt_template_hash": "81bf14f26f4fa761", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n---\n\nPick the single best beverage for a classic paella valenciana (rabbit, chicken, garrofó beans, saffron). Respond with just the candidate id.\n\nINPUT:\n{\n \"dish\": \"authentic paella valenciana\",\n \"candidates\": {\n \"a\": \"young Rioja crianza (Tempranillo blend, light oak)\",\n \"b\": \"Amarone della Valpolicella Riserva\",\n \"c\": \"Islay peated single malt\",\n \"d\": \"off-dry Moscato d'Asti\"\n }\n}\n\nANSWER FORMAT: one_of:a,b,c,d", "expected": { "value": "a", "ranking": [ "a", "b", "d", "c" ] }, "samples": [ { "sample": 0, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 392, "output_tokens": 1, "latency_ms": 8804.6, "usd": 0.0005, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 392, "output_tokens": 1, "latency_ms": 12392.4, "usd": 0.0005, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 392, "output_tokens": 1, "latency_ms": 10749.6, "usd": 0.0005, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 392.0, "output_tokens_mean": 1.0, "latency_ms_mean": 10648.867, "usd_sum": 0.0015 } }, { "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": 417, "output_tokens": 1, "latency_ms": 4503.5, "usd": 0.000531, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 417, "output_tokens": 1, "latency_ms": 3570.8, "usd": 0.000531, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 417, "output_tokens": 1, "latency_ms": 5119.5, "usd": 0.000531, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 417.0, "output_tokens_mean": 1.0, "latency_ms_mean": 4397.933, "usd_sum": 0.001593 } }, { "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": 385, "output_tokens": 1, "latency_ms": 11660.5, "usd": 0.000491, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 385, "output_tokens": 1, "latency_ms": 9342.7, "usd": 0.000491, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 385, "output_tokens": 1, "latency_ms": 10739.9, "usd": 0.000491, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 10581.033, "usd_sum": 0.001473 } }, { "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": 371, "output_tokens": 1, "latency_ms": 11050.9, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 9634.0, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 14131.5, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 371.0, "output_tokens_mean": 1.0, "latency_ms_mean": 11605.467, "usd_sum": 0.001422 } }, { "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": 367, "output_tokens": 1, "latency_ms": 12111.0, "usd": 0.000469, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 367, "output_tokens": 1, "latency_ms": 11324.2, "usd": 0.000469, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 367, "output_tokens": 1, "latency_ms": 13016.7, "usd": 0.000469, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 367.0, "output_tokens_mean": 1.0, "latency_ms_mean": 12150.633, "usd_sum": 0.001407 } }, { "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": 382, "output_tokens": 1, "latency_ms": 14539.3, "usd": 0.000488, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 382, "output_tokens": 1, "latency_ms": 15923.2, "usd": 0.000488, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 382, "output_tokens": 1, "latency_ms": 13212.4, "usd": 0.000488, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 382.0, "output_tokens_mean": 1.0, "latency_ms_mean": 14558.3, "usd_sum": 0.001464 } }, { "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": 363, "output_tokens": 1, "latency_ms": 10554.7, "usd": 0.000464, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 363, "output_tokens": 1, "latency_ms": 9541.4, "usd": 0.000464, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 363, "output_tokens": 1, "latency_ms": 12017.1, "usd": 0.000464, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 363.0, "output_tokens_mean": 1.0, "latency_ms_mean": 10704.4, "usd_sum": 0.001392 } }, { "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": 365, "output_tokens": 1, "latency_ms": 13798.0, "usd": 0.000466, "model_version": "gemini-2.5-pro", "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": 1, "latency_ms": 13013.2, "usd": 0.000466, "model_version": "gemini-2.5-pro", "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": 1, "latency_ms": 14235.2, "usd": 0.000466, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 365.0, "output_tokens_mean": 1.0, "latency_ms_mean": 13682.133, "usd_sum": 0.001398 } }, { "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": 368, "output_tokens": 1, "latency_ms": 12236.3, "usd": 0.00047, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 368, "output_tokens": 1, "latency_ms": 10972.7, "usd": 0.00047, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 368, "output_tokens": 1, "latency_ms": 13140.7, "usd": 0.00047, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 368.0, "output_tokens_mean": 1.0, "latency_ms_mean": 12116.567, "usd_sum": 0.00141 } }, { "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": 389, "output_tokens": 1, "latency_ms": 12387.7, "usd": 0.000496, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 389, "output_tokens": 1, "latency_ms": 13106.1, "usd": 0.000496, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 389, "output_tokens": 1, "latency_ms": 12427.8, "usd": 0.000496, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 389.0, "output_tokens_mean": 1.0, "latency_ms_mean": 12640.533, "usd_sum": 0.001488 } }, { "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": 372, "output_tokens": 1, "latency_ms": 12146.4, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 372, "output_tokens": 1, "latency_ms": 11360.6, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 372, "output_tokens": 1, "latency_ms": 11246.1, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 372.0, "output_tokens_mean": 1.0, "latency_ms_mean": 11584.367, "usd_sum": 0.001425 } }, { "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": 371, "output_tokens": 1, "latency_ms": 12208.7, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 15874.6, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 12137.7, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 371.0, "output_tokens_mean": 1.0, "latency_ms_mean": 13407.0, "usd_sum": 0.001422 } }, { "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": 367, "output_tokens": 1, "latency_ms": 15709.7, "usd": 0.000469, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 367, "output_tokens": 1, "latency_ms": 13721.3, "usd": 0.000469, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 367, "output_tokens": 1, "latency_ms": 12085.7, "usd": 0.000469, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 367.0, "output_tokens_mean": 1.0, "latency_ms_mean": 13838.9, "usd_sum": 0.001407 } }, { "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": 402, "output_tokens": 2, "latency_ms": 3420.1, "usd": 0.000523, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 2, "latency_ms": 4026.4, "usd": 0.000523, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 2, "latency_ms": 3403.9, "usd": 0.000523, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 402.0, "output_tokens_mean": 2.0, "latency_ms_mean": 3616.8, "usd_sum": 0.001569 } }, { "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": 250, "output_tokens": 3, "latency_ms": 2337.9, "usd": 0.000343, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 250, "output_tokens": 3, "latency_ms": 1859.9, "usd": 0.000343, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 250, "output_tokens": 3, "latency_ms": 4605.2, "usd": 0.000343, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 250.0, "output_tokens_mean": 3.0, "latency_ms_mean": 2934.333, "usd_sum": 0.001029 } }, { "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": 249, "output_tokens": 2, "latency_ms": 2153.3, "usd": 0.000331, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 249, "output_tokens": 2, "latency_ms": 2278.0, "usd": 0.000331, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 249, "output_tokens": 2, "latency_ms": 3330.3, "usd": 0.000331, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 2.0, "latency_ms_mean": 2587.2, "usd_sum": 0.000993 } }, { "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": 245, "output_tokens": 1, "latency_ms": 1952.9, "usd": 0.000316, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 245, "output_tokens": 1, "latency_ms": 2265.9, "usd": 0.000316, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 245, "output_tokens": 1, "latency_ms": 2253.0, "usd": 0.000316, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 2157.267, "usd_sum": 0.000948 } }, { "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": 254, "output_tokens": 5, "latency_ms": 8695.9, "usd": 0.000368, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Gewürztraminer", "compliant": true, "score": 0.0, "detail": { "predicted": "gewürztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 254, "output_tokens": 4, "latency_ms": 7738.5, "usd": 0.000358, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Gewürztraminer", "compliant": true, "score": 0.0, "detail": { "predicted": "gewürztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 254, "output_tokens": 4, "latency_ms": 8036.6, "usd": 0.000358, "model_version": "gemini-2.5-pro", "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": 254.0, "output_tokens_mean": 4.333, "latency_ms_mean": 8157.0, "usd_sum": 0.001084 } }, { "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": 260, "output_tokens": 3, "latency_ms": 4019.3, "usd": 0.000355, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 260, "output_tokens": 3, "latency_ms": 4260.7, "usd": 0.000355, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 260, "output_tokens": 3, "latency_ms": 4416.4, "usd": 0.000355, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 260.0, "output_tokens_mean": 3.0, "latency_ms_mean": 4232.133, "usd_sum": 0.001065 } }, { "task_id": "ogs:core:benchmark-task:region-006", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "medium", "cuisine_region": "spanish", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "979e7579b34d9797", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhat is the name of the official Rioja classification for a red wine aged at least 2 years (1 in oak) and 3+ years total? Respond with just the term.\n\nINPUT:\n{\n \"question\": \"official Rioja classification for red wine aged 2+ years (1+ in oak), 3+ total\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "reserva" }, "samples": [ { "sample": 0, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 306, "output_tokens": 2, "latency_ms": 7779.4, "usd": 0.000402, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 306, "output_tokens": 2, "latency_ms": 8333.7, "usd": 0.000402, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 306, "output_tokens": 2, "latency_ms": 9687.4, "usd": 0.000402, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 306.0, "output_tokens_mean": 2.0, "latency_ms_mean": 8600.167, "usd_sum": 0.001206 } }, { "task_id": "ogs:core:benchmark-task:region-007", "category": "regional", "capability": "dish_origin", "difficulty": "easy", "cuisine_region": "korean", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "23a69016b1082553", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nFrom which country does kimchi originate? Respond with just the country name in English.\n\nINPUT:\n{\n \"dish\": \"kimchi\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "korea", "aliases": [ "south korea", "republic of korea" ] }, "samples": [ { "sample": 0, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 264, "output_tokens": 1, "latency_ms": 3656.4, "usd": 0.00034, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 264, "output_tokens": 1, "latency_ms": 4384.6, "usd": 0.00034, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 264, "output_tokens": 1, "latency_ms": 6840.0, "usd": 0.00034, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 264.0, "output_tokens_mean": 1.0, "latency_ms_mean": 4960.333, "usd_sum": 0.00102 } }, { "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": 265, "output_tokens": 3, "latency_ms": 2759.3, "usd": 0.000361, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 265, "output_tokens": 3, "latency_ms": 3152.9, "usd": 0.000361, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 265, "output_tokens": 3, "latency_ms": 4600.4, "usd": 0.000361, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 3.0, "latency_ms_mean": 3504.2, "usd_sum": 0.001083 } }, { "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": 265, "output_tokens": 1, "latency_ms": 4196.5, "usd": 0.000341, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 265, "output_tokens": 1, "latency_ms": 5118.8, "usd": 0.000341, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 265, "output_tokens": 1, "latency_ms": 4034.8, "usd": 0.000341, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 4450.033, "usd_sum": 0.001023 } }, { "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": 268, "output_tokens": 1, "latency_ms": 2623.3, "usd": 0.000345, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 268, "output_tokens": 1, "latency_ms": 2997.4, "usd": 0.000345, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 268, "output_tokens": 1, "latency_ms": 2252.9, "usd": 0.000345, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 268.0, "output_tokens_mean": 1.0, "latency_ms_mean": 2624.533, "usd_sum": 0.001035 } }, { "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": "Chablis", "compliant": true, "score": 1.0, "detail": { "predicted": "chablis", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 272, "output_tokens": 3, "latency_ms": 7249.1, "usd": 0.00037, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Chablis", "compliant": true, "score": 1.0, "detail": { "predicted": "chablis", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 272, "output_tokens": 3, "latency_ms": 9203.2, "usd": 0.00037, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Chablis", "compliant": true, "score": 1.0, "detail": { "predicted": "chablis", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 272, "output_tokens": 3, "latency_ms": 7984.0, "usd": 0.00037, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 272.0, "output_tokens_mean": 3.0, "latency_ms_mean": 8145.433, "usd_sum": 0.00111 } }, { "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": 275, "output_tokens": 3, "latency_ms": 3251.9, "usd": 0.000374, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 275, "output_tokens": 2, "latency_ms": 3365.5, "usd": 0.000364, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 275, "output_tokens": 2, "latency_ms": 4238.6, "usd": 0.000364, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 275.0, "output_tokens_mean": 2.333, "latency_ms_mean": 3618.667, "usd_sum": 0.001102 } }, { "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": 262, "output_tokens": 1, "latency_ms": 2148.2, "usd": 0.000338, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 262, "output_tokens": 1, "latency_ms": 2525.1, "usd": 0.000338, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 262, "output_tokens": 1, "latency_ms": 2390.6, "usd": 0.000338, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 2354.633, "usd_sum": 0.001014 } }, { "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": 269, "output_tokens": 2, "latency_ms": 2997.3, "usd": 0.000356, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 269, "output_tokens": 2, "latency_ms": 2633.5, "usd": 0.000356, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 269, "output_tokens": 2, "latency_ms": 2658.3, "usd": 0.000356, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 269.0, "output_tokens_mean": 2.0, "latency_ms_mean": 2763.033, "usd_sum": 0.001068 } }, { "task_id": "ogs:core:benchmark-task:region-015", "category": "regional", "capability": "wine_region_knowledge", "difficulty": "hard", "cuisine_region": "french", "scorer": "exact_match", "context_needs": [], "prompt_template_hash": "2f35d24bb9d58118", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n---\n\nWhat single grape variety is used for white Sancerre AOC?\n\nINPUT:\n{\n \"wine\": \"Sancerre AOC blanc\"\n}\n\nANSWER FORMAT: one_word", "expected": { "value": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "samples": [ { "sample": 0, "raw_response": "Sauvignon", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 264, "output_tokens": 3, "latency_ms": 11233.4, "usd": 0.00036, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Sauvignon", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 264, "output_tokens": 3, "latency_ms": 13379.9, "usd": 0.00036, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Sauvignon", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 264, "output_tokens": 3, "latency_ms": 14664.4, "usd": 0.00036, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 264.0, "output_tokens_mean": 3.0, "latency_ms_mean": 13092.567, "usd_sum": 0.00108 } }, { "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": 258, "output_tokens": 1, "latency_ms": 2310.5, "usd": 0.000333, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 258, "output_tokens": 1, "latency_ms": 2650.3, "usd": 0.000333, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 258, "output_tokens": 1, "latency_ms": 1864.1, "usd": 0.000333, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 258.0, "output_tokens_mean": 1.0, "latency_ms_mean": 2274.967, "usd_sum": 0.000999 } }, { "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": 266, "output_tokens": 3, "latency_ms": 5912.4, "usd": 0.000363, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 266, "output_tokens": 3, "latency_ms": 6349.8, "usd": 0.000363, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 266, "output_tokens": 3, "latency_ms": 8076.0, "usd": 0.000363, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 266.0, "output_tokens_mean": 3.0, "latency_ms_mean": 6779.4, "usd_sum": 0.001089 } }, { "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": 262, "output_tokens": 1, "latency_ms": 2962.6, "usd": 0.000338, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 262, "output_tokens": 1, "latency_ms": 3501.3, "usd": 0.000338, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 262, "output_tokens": 1, "latency_ms": 3788.5, "usd": 0.000338, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 3417.467, "usd_sum": 0.001014 } }, { "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": 272, "output_tokens": 1, "latency_ms": 3478.8, "usd": 0.00035, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 272, "output_tokens": 1, "latency_ms": 2667.0, "usd": 0.00035, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 272, "output_tokens": 1, "latency_ms": 2967.7, "usd": 0.00035, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 272.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3037.833, "usd_sum": 0.00105 } }, { "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": 286, "output_tokens": 3, "latency_ms": 6765.5, "usd": 0.000388, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 286, "output_tokens": 3, "latency_ms": 8168.2, "usd": 0.000388, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 286, "output_tokens": 3, "latency_ms": 6364.6, "usd": 0.000388, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 286.0, "output_tokens_mean": 3.0, "latency_ms_mean": 7099.433, "usd_sum": 0.001164 } }, { "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": 691, "output_tokens": 8, "latency_ms": 10028.5, "usd": 0.000944, "model_version": "gemini-2.5-pro", "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": 691, "output_tokens": 8, "latency_ms": 10501.0, "usd": 0.000944, "model_version": "gemini-2.5-pro", "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": 691, "output_tokens": 8, "latency_ms": 11308.3, "usd": 0.000944, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 691.0, "output_tokens_mean": 8.0, "latency_ms_mean": 10612.6, "usd_sum": 0.002832 } }, { "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": 696, "output_tokens": 9, "latency_ms": 7518.8, "usd": 0.00096, "model_version": "gemini-2.5-pro", "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": 696, "output_tokens": 9, "latency_ms": 7253.9, "usd": 0.00096, "model_version": "gemini-2.5-pro", "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": 696, "output_tokens": 9, "latency_ms": 6751.9, "usd": 0.00096, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 696.0, "output_tokens_mean": 9.0, "latency_ms_mean": 7174.867, "usd_sum": 0.00288 } }, { "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": 696, "output_tokens": 8, "latency_ms": 12471.8, "usd": 0.00095, "model_version": "gemini-2.5-pro", "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": 696, "output_tokens": 8, "latency_ms": 12591.8, "usd": 0.00095, "model_version": "gemini-2.5-pro", "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": 696, "output_tokens": 8, "latency_ms": 10957.4, "usd": 0.00095, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 696.0, "output_tokens_mean": 8.0, "latency_ms_mean": 12007.0, "usd_sum": 0.00285 } }, { "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": 641, "output_tokens": 1, "latency_ms": 6263.9, "usd": 0.000811, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 641, "output_tokens": 1, "latency_ms": 7194.6, "usd": 0.000811, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 641, "output_tokens": 1, "latency_ms": 5353.0, "usd": 0.000811, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 6270.5, "usd_sum": 0.002433 } }, { "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": 688, "output_tokens": 8, "latency_ms": 7320.4, "usd": 0.00094, "model_version": "gemini-2.5-pro", "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": 688, "output_tokens": 8, "latency_ms": 7138.3, "usd": 0.00094, "model_version": "gemini-2.5-pro", "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": 688, "output_tokens": 8, "latency_ms": 9246.6, "usd": 0.00094, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 688.0, "output_tokens_mean": 8.0, "latency_ms_mean": 7901.767, "usd_sum": 0.00282 } }, { "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": 692, "output_tokens": 8, "latency_ms": 11592.9, "usd": 0.000945, "model_version": "gemini-2.5-pro", "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": 692, "output_tokens": 8, "latency_ms": 9610.3, "usd": 0.000945, "model_version": "gemini-2.5-pro", "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": 692, "output_tokens": 8, "latency_ms": 11427.3, "usd": 0.000945, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 692.0, "output_tokens_mean": 8.0, "latency_ms_mean": 10876.833, "usd_sum": 0.002835 } }, { "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": 697, "output_tokens": 9, "latency_ms": 9114.7, "usd": 0.000961, "model_version": "gemini-2.5-pro", "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": 697, "output_tokens": 9, "latency_ms": 8332.7, "usd": 0.000961, "model_version": "gemini-2.5-pro", "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": 697, "output_tokens": 9, "latency_ms": 8557.8, "usd": 0.000961, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 697.0, "output_tokens_mean": 9.0, "latency_ms_mean": 8668.4, "usd_sum": 0.002883 } }, { "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": 695, "output_tokens": 9, "latency_ms": 8090.9, "usd": 0.000959, "model_version": "gemini-2.5-pro", "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": 695, "output_tokens": 9, "latency_ms": 8084.4, "usd": 0.000959, "model_version": "gemini-2.5-pro", "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": 695, "output_tokens": 9, "latency_ms": 8744.2, "usd": 0.000959, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 695.0, "output_tokens_mean": 9.0, "latency_ms_mean": 8306.5, "usd_sum": 0.002877 } }, { "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": 693, "output_tokens": 8, "latency_ms": 11630.3, "usd": 0.000946, "model_version": "gemini-2.5-pro", "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": 693, "output_tokens": 8, "latency_ms": 10700.5, "usd": 0.000946, "model_version": "gemini-2.5-pro", "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": 693, "output_tokens": 8, "latency_ms": 9984.9, "usd": 0.000946, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 693.0, "output_tokens_mean": 8.0, "latency_ms_mean": 10771.9, "usd_sum": 0.002838 } }, { "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": 690, "output_tokens": 8, "latency_ms": 10722.8, "usd": 0.000942, "model_version": "gemini-2.5-pro", "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": 690, "output_tokens": 8, "latency_ms": 10468.9, "usd": 0.000942, "model_version": "gemini-2.5-pro", "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": 690, "output_tokens": 8, "latency_ms": 8109.3, "usd": 0.000942, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 690.0, "output_tokens_mean": 8.0, "latency_ms_mean": 9767.0, "usd_sum": 0.002826 } }, { "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": 696, "output_tokens": 8, "latency_ms": 7739.9, "usd": 0.00095, "model_version": "gemini-2.5-pro", "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": 696, "output_tokens": 8, "latency_ms": 8406.5, "usd": 0.00095, "model_version": "gemini-2.5-pro", "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": 696, "output_tokens": 8, "latency_ms": 8610.4, "usd": 0.00095, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 696.0, "output_tokens_mean": 8.0, "latency_ms_mean": 8252.267, "usd_sum": 0.00285 } }, { "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": 686, "output_tokens": 8, "latency_ms": 9825.5, "usd": 0.000937, "model_version": "gemini-2.5-pro", "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": 686, "output_tokens": 8, "latency_ms": 11057.9, "usd": 0.000937, "model_version": "gemini-2.5-pro", "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": 686, "output_tokens": 8, "latency_ms": 9831.1, "usd": 0.000937, "model_version": "gemini-2.5-pro", "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": 686.0, "output_tokens_mean": 8.0, "latency_ms_mean": 10238.167, "usd_sum": 0.002811 } }, { "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": 688, "output_tokens": 10, "latency_ms": 7626.8, "usd": 0.00096, "model_version": "gemini-2.5-pro", "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": 688, "output_tokens": 10, "latency_ms": 11294.9, "usd": 0.00096, "model_version": "gemini-2.5-pro", "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": 688, "output_tokens": 10, "latency_ms": 9162.4, "usd": 0.00096, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 688.0, "output_tokens_mean": 10.0, "latency_ms_mean": 9361.367, "usd_sum": 0.00288 } }, { "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": 691, "output_tokens": 8, "latency_ms": 7842.2, "usd": 0.000944, "model_version": "gemini-2.5-pro", "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": 691, "output_tokens": 8, "latency_ms": 10360.2, "usd": 0.000944, "model_version": "gemini-2.5-pro", "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": 691, "output_tokens": 8, "latency_ms": 10535.4, "usd": 0.000944, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 691.0, "output_tokens_mean": 8.0, "latency_ms_mean": 9579.267, "usd_sum": 0.002832 } }, { "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_INTENSITY_MISMATCH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 691, "output_tokens": 8, "latency_ms": 8088.5, "usd": 0.000944, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 691, "output_tokens": 8, "latency_ms": 10137.6, "usd": 0.000944, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_bitter_amplify", "aliases": [] }, "metrics": { "input_tokens": 691, "output_tokens": 8, "latency_ms": 9247.2, "usd": 0.000944, "model_version": "gemini-2.5-pro", "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": 691.0, "output_tokens_mean": 8.0, "latency_ms_mean": 9157.767, "usd_sum": 0.002832 } }, { "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": 690, "output_tokens": 9, "latency_ms": 7433.9, "usd": 0.000953, "model_version": "gemini-2.5-pro", "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": 690, "output_tokens": 9, "latency_ms": 7847.8, "usd": 0.000953, "model_version": "gemini-2.5-pro", "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": 690, "output_tokens": 9, "latency_ms": 8190.7, "usd": 0.000953, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 690.0, "output_tokens_mean": 9.0, "latency_ms_mean": 7824.133, "usd_sum": 0.002859 } }, { "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": 639, "output_tokens": 1, "latency_ms": 6085.3, "usd": 0.000809, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 1, "latency_ms": 6755.8, "usd": 0.000809, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 639, "output_tokens": 1, "latency_ms": 6607.9, "usd": 0.000809, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.0, "score_summary": { "mean": 0.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.0, "ci95_hi": 0.0, "n": 3 }, "score_if_valid": 0.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 639.0, "output_tokens_mean": 1.0, "latency_ms_mean": 6483.0, "usd_sum": 0.002427 } }, { "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": 626, "output_tokens": 1, "latency_ms": 4959.1, "usd": 0.000793, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 626, "output_tokens": 1, "latency_ms": 5305.7, "usd": 0.000793, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 626, "output_tokens": 1, "latency_ms": 5102.0, "usd": 0.000793, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 626.0, "output_tokens_mean": 1.0, "latency_ms_mean": 5122.267, "usd_sum": 0.002379 } }, { "task_id": "ogs:core:benchmark-task:risk-019", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "german", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "0e3d6c3f9d86af0b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"raw Kumamoto oyster\",\n \"beverage\": \"off-dry Spätlese Riesling with 45 g/L residual sugar\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SWEETNESS_CONFLICT" }, "samples": [ { "sample": 0, "raw_response": "RISK_INTENSITY_MISMATCH", "compliant": true, "score": 0.0, "detail": { "predicted": "risk_intensity_mismatch", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 697, "output_tokens": 8, "latency_ms": 22630.6, "usd": 0.000951, "model_version": "gemini-2.5-pro", "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": 697, "output_tokens": 8, "latency_ms": 9761.4, "usd": 0.000951, "model_version": "gemini-2.5-pro", "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": 697, "output_tokens": 8, "latency_ms": 11465.2, "usd": 0.000951, "model_version": "gemini-2.5-pro", "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": 697.0, "output_tokens_mean": 8.0, "latency_ms_mean": 14619.067, "usd_sum": 0.002853 } }, { "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": 700, "output_tokens": 8, "latency_ms": 7578.6, "usd": 0.000955, "model_version": "gemini-2.5-pro", "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": 700, "output_tokens": 8, "latency_ms": 7502.1, "usd": 0.000955, "model_version": "gemini-2.5-pro", "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": 700, "output_tokens": 8, "latency_ms": 8029.2, "usd": 0.000955, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 700.0, "output_tokens_mean": 8.0, "latency_ms_mean": 7703.3, "usd_sum": 0.002865 } }, { "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": 823, "output_tokens": 2, "latency_ms": 3018.8, "usd": 0.001049, "model_version": "gemini-2.5-pro", "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": 823, "output_tokens": 2, "latency_ms": 3336.8, "usd": 0.001049, "model_version": "gemini-2.5-pro", "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": 823, "output_tokens": 2, "latency_ms": 2837.3, "usd": 0.001049, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 823.0, "output_tokens_mean": 2.0, "latency_ms_mean": 3064.3, "usd_sum": 0.003147 } }, { "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": 822, "output_tokens": 2, "latency_ms": 5070.3, "usd": 0.001048, "model_version": "gemini-2.5-pro", "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": 822, "output_tokens": 2, "latency_ms": 5427.1, "usd": 0.001048, "model_version": "gemini-2.5-pro", "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": 822, "output_tokens": 2, "latency_ms": 4330.0, "usd": 0.001048, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 822.0, "output_tokens_mean": 2.0, "latency_ms_mean": 4942.467, "usd_sum": 0.003144 } }, { "task_id": "ogs:core:benchmark-task:safe-003", "category": "safety", "capability": "danger_zone", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "97f1d8e6fc44b9e2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nThe bacterial danger zone is defined between two temperatures in °C. Respond as 'LOW-HIGH' in °C (integers), e.g. '10-50'.\n\nANSWER FORMAT: exact:LOW-HIGH °C", "expected": { "value": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "samples": [ { "sample": 0, "raw_response": "exact:5-63 °C", "compliant": true, "score": 0.0, "detail": { "predicted": "exact:5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 817, "output_tokens": 8, "latency_ms": 3243.2, "usd": 0.001101, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "exact:5-63 °C", "compliant": true, "score": 0.0, "detail": { "predicted": "exact:5-63 °c", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 817, "output_tokens": 8, "latency_ms": 3350.1, "usd": 0.001101, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "5-63", "compliant": true, "score": 1.0, "detail": { "predicted": "5-63", "expected": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "metrics": { "input_tokens": 817, "output_tokens": 4, "latency_ms": 3125.9, "usd": 0.001061, "model_version": "gemini-2.5-pro", "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": 817.0, "output_tokens_mean": 6.667, "latency_ms_mean": 3239.733, "usd_sum": 0.003263 } }, { "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": 810, "output_tokens": 1, "latency_ms": 3184.1, "usd": 0.001022, "model_version": "gemini-2.5-pro", "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": 810, "output_tokens": 1, "latency_ms": 2933.2, "usd": 0.001022, "model_version": "gemini-2.5-pro", "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": 810, "output_tokens": 1, "latency_ms": 3487.1, "usd": 0.001022, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 810.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3201.467, "usd_sum": 0.003066 } }, { "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": 807, "output_tokens": 2, "latency_ms": 3251.9, "usd": 0.001029, "model_version": "gemini-2.5-pro", "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": 807, "output_tokens": 2, "latency_ms": 3907.3, "usd": 0.001029, "model_version": "gemini-2.5-pro", "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": 807, "output_tokens": 2, "latency_ms": 3891.5, "usd": 0.001029, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 807.0, "output_tokens_mean": 2.0, "latency_ms_mean": 3683.567, "usd_sum": 0.003087 } }, { "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": 798, "output_tokens": 2, "latency_ms": 2565.8, "usd": 0.001017, "model_version": "gemini-2.5-pro", "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": 798, "output_tokens": 2, "latency_ms": 3296.2, "usd": 0.001017, "model_version": "gemini-2.5-pro", "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": 798, "output_tokens": 2, "latency_ms": 2327.8, "usd": 0.001017, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 798.0, "output_tokens_mean": 2.0, "latency_ms_mean": 2729.933, "usd_sum": 0.003051 } }, { "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": 802, "output_tokens": 3, "latency_ms": 3375.4, "usd": 0.001032, "model_version": "gemini-2.5-pro", "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": 802, "output_tokens": 3, "latency_ms": 2980.3, "usd": 0.001032, "model_version": "gemini-2.5-pro", "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": 802, "output_tokens": 3, "latency_ms": 4596.4, "usd": 0.001032, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 802.0, "output_tokens_mean": 3.0, "latency_ms_mean": 3650.7, "usd_sum": 0.003096 } }, { "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": 887, "output_tokens": 6, "latency_ms": 4423.9, "usd": 0.001169, "model_version": "gemini-2.5-pro", "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": 887, "output_tokens": 6, "latency_ms": 5334.7, "usd": 0.001169, "model_version": "gemini-2.5-pro", "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": 887, "output_tokens": 6, "latency_ms": 4358.0, "usd": 0.001169, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 887.0, "output_tokens_mean": 6.0, "latency_ms_mean": 4705.533, "usd_sum": 0.003507 } }, { "task_id": "ogs:core:benchmark-task:safe-009", "category": "safety", "capability": "ccp_identification", "difficulty": "medium", "cuisine_region": "global", "scorer": "set_f1", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "9f4b49c1c20e4376", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nFor a cook-chill dish of chicken curry with rice, identify the Critical Control Points from the OGS stage list. Return a comma-separated list using the OGS CCP stage IDs.\n\nINPUT:\n{\n \"dish\": \"cook-chill chicken curry with rice\"\n}\n\nANSWER FORMAT: set:comma-separated CCP stage IDs", "expected": { "values": [ "cooking", "cooling", "storage_cold", "reheating", "hot_holding" ] }, "samples": [ { "sample": 0, "raw_response": "receiving,storage_cold,cooking,cooling,reheating", "compliant": true, "score": 0.8, "detail": { "predicted": [ "cooking", "cooling", "receiving", "reheating", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 839, "output_tokens": 12, "latency_ms": 12165.0, "usd": 0.001169, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "receiving,storage_cold,thawing,cooking,cooling,reheating,hot_holding", "compliant": true, "score": 0.8333, "detail": { "predicted": [ "cooking", "cooling", "hot_holding", "receiving", "reheating", "storage_cold", "thawing" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.7143, "recall": 1.0 }, "metrics": { "input_tokens": 839, "output_tokens": 19, "latency_ms": 25269.5, "usd": 0.001239, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "receiving,storage_cold,cooking,cooling,reheating,hot_holding", "compliant": true, "score": 0.9091, "detail": { "predicted": [ "cooking", "cooling", "hot_holding", "receiving", "reheating", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.8333, "recall": 1.0 }, "metrics": { "input_tokens": 839, "output_tokens": 16, "latency_ms": 21811.1, "usd": 0.001209, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.8475, "score_summary": { "mean": 0.8475, "stdev": 0.0559, "sem": 0.0323, "ci95_lo": 0.7842, "ci95_hi": 0.9107, "n": 3 }, "score_if_valid": 0.8475, "format_rate": 1.0, "metrics": { "input_tokens_mean": 839.0, "output_tokens_mean": 15.667, "latency_ms_mean": 19748.533, "usd_sum": 0.003617 } }, { "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": 843, "output_tokens": 1, "latency_ms": 5333.7, "usd": 0.001064, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 843, "output_tokens": 1, "latency_ms": 5012.1, "usd": 0.001064, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 843, "output_tokens": 1, "latency_ms": 3938.2, "usd": 0.001064, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 843.0, "output_tokens_mean": 1.0, "latency_ms_mean": 4761.333, "usd_sum": 0.003192 } }, { "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": 899, "output_tokens": 5, "latency_ms": 6616.7, "usd": 0.001174, "model_version": "gemini-2.5-pro", "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": 899, "output_tokens": 5, "latency_ms": 9332.6, "usd": 0.001174, "model_version": "gemini-2.5-pro", "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": 899, "output_tokens": 5, "latency_ms": 10367.6, "usd": 0.001174, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 899.0, "output_tokens_mean": 5.0, "latency_ms_mean": 8772.3, "usd_sum": 0.003522 } }, { "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": 865, "output_tokens": 19, "latency_ms": 5625.5, "usd": 0.001271, "model_version": "gemini-2.5-pro", "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": 865, "output_tokens": 19, "latency_ms": 5858.6, "usd": 0.001271, "model_version": "gemini-2.5-pro", "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": 865, "output_tokens": 19, "latency_ms": 7353.2, "usd": 0.001271, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 865.0, "output_tokens_mean": 19.0, "latency_ms_mean": 6279.1, "usd_sum": 0.003813 } }, { "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": "9.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 402, "output_tokens": 3, "latency_ms": 26146.7, "usd": 0.000532, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "9.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 402, "output_tokens": 3, "latency_ms": 11626.9, "usd": 0.000532, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "9.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 402, "output_tokens": 3, "latency_ms": 10205.6, "usd": 0.000532, "model_version": "gemini-2.5-pro", "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": 402.0, "output_tokens_mean": 3.0, "latency_ms_mean": 15993.067, "usd_sum": 0.001596 } }, { "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": 377, "output_tokens": 3, "latency_ms": 7073.7, "usd": 0.000501, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "9.5", "compliant": true, "score": 1.0, "detail": { "predicted": 9.5, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 377, "output_tokens": 3, "latency_ms": 12186.0, "usd": 0.000501, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "9.5", "compliant": true, "score": 1.0, "detail": { "predicted": 9.5, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 377, "output_tokens": 3, "latency_ms": 13244.6, "usd": 0.000501, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 3.0, "latency_ms_mean": 10834.767, "usd_sum": 0.001503 } }, { "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": "9", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 366, "output_tokens": 1, "latency_ms": 6963.0, "usd": 0.000468, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "9", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 366, "output_tokens": 1, "latency_ms": 7199.9, "usd": 0.000468, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "9", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 366, "output_tokens": 1, "latency_ms": 10524.4, "usd": 0.000468, "model_version": "gemini-2.5-pro", "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": 366.0, "output_tokens_mean": 1.0, "latency_ms_mean": 8229.1, "usd_sum": 0.001404 } }, { "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": "```json\n{\n \"sweet\": 7.5,\n \"sour\": 4.0,\n \"salty\": 0.0,\n \"bitter\": 0.0,\n \"umami\": 0.5\n}\n```", "compliant": true, "score": 0.8, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 4.0, "expected": 4.0, "score": 1.0 }, "salty": { "predicted": 0.0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.0, "expected": 1.0, "score": 0.5 }, "umami": { "predicted": 0.5, "expected": 0.5, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 616, "output_tokens": 60, "latency_ms": 7081.5, "usd": 0.00137, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"sweet\": 8.0,\n \"sour\": 4.5,\n \"salty\": 0.0,\n \"bitter\": 0.0,\n \"umami\": 0.0\n}\n```", "compliant": true, "score": 0.65, "detail": { "per_key": { "sweet": { "predicted": 8.0, "expected": 7.0, "score": 0.5 }, "sour": { "predicted": 4.5, "expected": 4.0, "score": 0.75 }, "salty": { "predicted": 0.0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.0, "expected": 1.0, "score": 0.5 }, "umami": { "predicted": 0.0, "expected": 0.5, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 616, "output_tokens": 60, "latency_ms": 6656.8, "usd": 0.00137, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"sweet\": 7.5,\n \"sour\": 4.0,\n \"salty\": 0.0,\n \"bitter\": 0.0,\n \"umami\": 0.0\n}\n```", "compliant": true, "score": 0.75, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 4.0, "expected": 4.0, "score": 1.0 }, "salty": { "predicted": 0.0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.0, "expected": 1.0, "score": 0.5 }, "umami": { "predicted": 0.0, "expected": 0.5, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 616, "output_tokens": 60, "latency_ms": 5881.3, "usd": 0.00137, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.7333, "score_summary": { "mean": 0.7333, "stdev": 0.0764, "sem": 0.0441, "ci95_lo": 0.6469, "ci95_hi": 0.8198, "n": 3 }, "score_if_valid": 0.7333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 616.0, "output_tokens_mean": 60.0, "latency_ms_mean": 6539.867, "usd_sum": 0.00411 } }, { "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": "8", "compliant": true, "score": 0.3333, "detail": { "predicted": 8.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 9856.7, "usd": 0.00049, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "8", "compliant": true, "score": 0.3333, "detail": { "predicted": 8.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 9269.0, "usd": 0.00049, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "8", "compliant": true, "score": 0.3333, "detail": { "predicted": 8.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 384, "output_tokens": 1, "latency_ms": 8887.8, "usd": 0.00049, "model_version": "gemini-2.5-pro", "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": 384.0, "output_tokens_mean": 1.0, "latency_ms_mean": 9337.833, "usd_sum": 0.00147 } }, { "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": "vegetal", "compliant": true, "score": 1.0, "detail": { "predicted": "vegetal", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 337, "output_tokens": 2, "latency_ms": 6450.3, "usd": 0.000441, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 0.0, "detail": { "predicted": "fruit", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 337, "output_tokens": 1, "latency_ms": 8467.7, "usd": 0.000431, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 0.0, "detail": { "predicted": "fruit", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 337, "output_tokens": 1, "latency_ms": 4504.4, "usd": 0.000431, "model_version": "gemini-2.5-pro", "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": 337.0, "output_tokens_mean": 1.333, "latency_ms_mean": 6474.133, "usd_sum": 0.001303 } }, { "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": "```json\n{\n \"body\": 4,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 2,\n \"effervescence\": 9\n}\n```", "compliant": true, "score": 0.7083, "detail": { "per_key": { "body": { "predicted": 4, "expected": 4.5, "score": 0.75 }, "acidity_perception": { "predicted": 8, "expected": 8.0, "score": 1.0 }, "tannin": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "astringency": { "predicted": 0, "expected": 1.0, "score": 0.5 }, "alcohol_heat": { "predicted": 2, "expected": 3.5, "score": 0.25 }, "effervescence": { "predicted": 9, "expected": 9.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 651, "output_tokens": 66, "latency_ms": 7882.9, "usd": 0.001474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"body\": 4,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 3,\n \"effervescence\": 9\n}\n```", "compliant": true, "score": 0.875, "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": 3, "expected": 3.5, "score": 0.75 }, "effervescence": { "predicted": 9, "expected": 9.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 651, "output_tokens": 66, "latency_ms": 8191.7, "usd": 0.001474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"body\": 4,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 2,\n \"effervescence\": 8\n}\n```", "compliant": true, "score": 0.7083, "detail": { "per_key": { "body": { "predicted": 4, "expected": 4.5, "score": 0.75 }, "acidity_perception": { "predicted": 8, "expected": 8.0, "score": 1.0 }, "tannin": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "astringency": { "predicted": 1, "expected": 1.0, "score": 1.0 }, "alcohol_heat": { "predicted": 2, "expected": 3.5, "score": 0.25 }, "effervescence": { "predicted": 8, "expected": 9.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 651, "output_tokens": 66, "latency_ms": 10224.3, "usd": 0.001474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.7639, "score_summary": { "mean": 0.7639, "stdev": 0.0962, "sem": 0.0556, "ci95_lo": 0.655, "ci95_hi": 0.8728, "n": 3 }, "score_if_valid": 0.7639, "format_rate": 1.0, "metrics": { "input_tokens_mean": 651.0, "output_tokens_mean": 66.0, "latency_ms_mean": 8766.3, "usd_sum": 0.004422 } }, { "task_id": "ogs:core:benchmark-task:sense-008", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "italian", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "873c6c2f9608e43f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the bitter intensity of raw radicchio on the OGS 0-10 intensity scale. Respond with only a single decimal number.\n\nINPUT:\n{\n \"ingredient\": \"raw radicchio\",\n \"attribute\": \"bitter\"\n}\n\nANSWER FORMAT: integer_0_10", "expected": { "value": 6.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "7", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 8459.5, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "7", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 9270.0, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "7", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 10649.7, "usd": 0.000474, "model_version": "gemini-2.5-pro", "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": 371.0, "output_tokens_mean": 1.0, "latency_ms_mean": 9459.733, "usd_sum": 0.001422 } }, { "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": "3.5", "compliant": true, "score": 0.0, "detail": { "predicted": 3.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 402, "output_tokens": 3, "latency_ms": 11106.9, "usd": 0.000532, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "1.5", "compliant": true, "score": 0.0, "detail": { "predicted": 1.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 402, "output_tokens": 3, "latency_ms": 10087.5, "usd": 0.000532, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "1.5", "compliant": true, "score": 0.0, "detail": { "predicted": 1.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 402, "output_tokens": 3, "latency_ms": 11533.8, "usd": 0.000532, "model_version": "gemini-2.5-pro", "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": 402.0, "output_tokens_mean": 3.0, "latency_ms_mean": 10909.4, "usd_sum": 0.001596 } }, { "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": 378, "output_tokens": 3, "latency_ms": 9866.7, "usd": 0.000503, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 0.0, "detail": { "predicted": 8.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 378, "output_tokens": 3, "latency_ms": 9098.2, "usd": 0.000503, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "8.5", "compliant": true, "score": 0.0, "detail": { "predicted": 8.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 378, "output_tokens": 3, "latency_ms": 9947.8, "usd": 0.000503, "model_version": "gemini-2.5-pro", "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": 378.0, "output_tokens_mean": 3.0, "latency_ms_mean": 9637.567, "usd_sum": 0.001509 } }, { "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": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 348, "output_tokens": 3, "latency_ms": 7260.1, "usd": 0.000465, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 348, "output_tokens": 3, "latency_ms": 6928.8, "usd": 0.000465, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 348, "output_tokens": 3, "latency_ms": 6597.3, "usd": 0.000465, "model_version": "gemini-2.5-pro", "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": 348.0, "output_tokens_mean": 3.0, "latency_ms_mean": 6928.733, "usd_sum": 0.001395 } }, { "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": "```json\n{\n \"sweet\": 7.5,\n \"sour\": 4.5,\n \"salty\": 0,\n \"bitter\": 0.5,\n \"umami\": 0\n}\n```", "compliant": true, "score": 0.85, "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": 0.5, "expected": 0.5, "score": 1.0 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 380, "output_tokens": 56, "latency_ms": 7938.8, "usd": 0.001035, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"sweet\": 7.5,\n \"sour\": 6.0,\n \"salty\": 0,\n \"bitter\": 1.0,\n \"umami\": 0\n}\n```", "compliant": true, "score": 0.85, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 6.0, "expected": 5.5, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 1.0, "expected": 0.5, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 380, "output_tokens": 56, "latency_ms": 7478.4, "usd": 0.001035, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"sweet\": 7.0,\n \"sour\": 5.0,\n \"salty\": 0.0,\n \"bitter\": 0.5,\n \"umami\": 0.0\n}\n```", "compliant": true, "score": 0.95, "detail": { "per_key": { "sweet": { "predicted": 7.0, "expected": 7.0, "score": 1.0 }, "sour": { "predicted": 5.0, "expected": 5.5, "score": 0.75 }, "salty": { "predicted": 0.0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 0.5, "expected": 0.5, "score": 1.0 }, "umami": { "predicted": 0.0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 380, "output_tokens": 60, "latency_ms": 9077.8, "usd": 0.001075, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.8833, "score_summary": { "mean": 0.8833, "stdev": 0.0577, "sem": 0.0333, "ci95_lo": 0.818, "ci95_hi": 0.9487, "n": 3 }, "score_if_valid": 0.8833, "format_rate": 1.0, "metrics": { "input_tokens_mean": 380.0, "output_tokens_mean": 57.333, "latency_ms_mean": 8165.0, "usd_sum": 0.003145 } }, { "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": 369, "output_tokens": 3, "latency_ms": 9496.0, "usd": 0.000491, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 369, "output_tokens": 3, "latency_ms": 7560.9, "usd": 0.000491, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "9.0", "compliant": true, "score": 1.0, "detail": { "predicted": 9.0, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 369, "output_tokens": 3, "latency_ms": 12916.1, "usd": 0.000491, "model_version": "gemini-2.5-pro", "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": 369.0, "output_tokens_mean": 3.0, "latency_ms_mean": 9991.0, "usd_sum": 0.001473 } }, { "task_id": "ogs:core:benchmark-task:sense-014", "category": "sensory", "capability": "dominant_aromatic_family", "difficulty": "medium", "cuisine_region": "scottish", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "c4a83a79265c0e9f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nIdentify the single dominant aromatic FAMILY (OGS vocabulary) of a heavily-peated Islay single malt (e.g. Ardbeg 10).\n\nINPUT:\n{\n \"item\": \"heavily peated Islay single malt whisky, ~50 ppm phenols\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "wood" }, "samples": [ { "sample": 0, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 353, "output_tokens": 1, "latency_ms": 19205.1, "usd": 0.000451, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 353, "output_tokens": 1, "latency_ms": 12233.4, "usd": 0.000451, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 353, "output_tokens": 1, "latency_ms": 13105.7, "usd": 0.000451, "model_version": "gemini-2.5-pro", "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": 353.0, "output_tokens_mean": 1.0, "latency_ms_mean": 14848.067, "usd_sum": 0.001353 } }, { "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": "```json\n{\n \"body\": 9,\n \"acidity_perception\": 6,\n \"tannin\": 8,\n \"astringency\": 8,\n \"alcohol_heat\": 8,\n \"effervescence\": 0\n}\n```", "compliant": true, "score": 0.7083, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 6, "expected": 6.0, "score": 1.0 }, "tannin": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "astringency": { "predicted": 8, "expected": 5.5, "score": 0.0 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 387, "output_tokens": 66, "latency_ms": 12235.6, "usd": 0.001144, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"body\": 9,\n \"acidity_perception\": 6,\n \"tannin\": 8,\n \"astringency\": 7,\n \"alcohol_heat\": 8,\n \"effervescence\": 0\n}\n```", "compliant": true, "score": 0.75, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 6, "expected": 6.0, "score": 1.0 }, "tannin": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "astringency": { "predicted": 7, "expected": 5.5, "score": 0.25 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 387, "output_tokens": 66, "latency_ms": 10495.6, "usd": 0.001144, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"body\": 10,\n \"acidity_perception\": 8,\n \"tannin\": 8,\n \"astringency\": 7,\n \"alcohol_heat\": 8,\n \"effervescence\": 0\n}\n```", "compliant": true, "score": 0.5, "detail": { "per_key": { "body": { "predicted": 10, "expected": 9.0, "score": 0.5 }, "acidity_perception": { "predicted": 8, "expected": 6.0, "score": 0.0 }, "tannin": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "astringency": { "predicted": 7, "expected": 5.5, "score": 0.25 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 387, "output_tokens": 67, "latency_ms": 7782.7, "usd": 0.001154, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.6528, "score_summary": { "mean": 0.6528, "stdev": 0.1339, "sem": 0.0773, "ci95_lo": 0.5012, "ci95_hi": 0.8043, "n": 3 }, "score_if_valid": 0.6528, "format_rate": 1.0, "metrics": { "input_tokens_mean": 387.0, "output_tokens_mean": 66.333, "latency_ms_mean": 10171.3, "usd_sum": 0.003442 } }, { "task_id": "ogs:core:benchmark-task:sense-016", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "spanish", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "70318c6fd3b033d2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the umami intensity of 24-month acorn-finished jamón ibérico de bellota on the OGS 0-10 scale.\n\nINPUT:\n{\n \"ingredient\": \"jamón ibérico de bellota, 24 months, acorn-finished\",\n \"attribute\": \"umami\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 8.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "7.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 388, "output_tokens": 3, "latency_ms": 13754.3, "usd": 0.000515, "model_version": "gemini-2.5-pro", "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": 388, "output_tokens": 3, "latency_ms": 11616.4, "usd": 0.000515, "model_version": "gemini-2.5-pro", "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": 388, "output_tokens": 3, "latency_ms": 10366.0, "usd": 0.000515, "model_version": "gemini-2.5-pro", "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": 388.0, "output_tokens_mean": 3.0, "latency_ms_mean": 11912.233, "usd_sum": 0.001545 } }, { "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": "spice", "compliant": true, "score": 0.0, "detail": { "predicted": "spice", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 1, "latency_ms": 7721.3, "usd": 0.000421, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "spice", "compliant": true, "score": 0.0, "detail": { "predicted": "spice", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 1, "latency_ms": 8403.8, "usd": 0.000421, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "spice", "compliant": true, "score": 0.0, "detail": { "predicted": "spice", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 329, "output_tokens": 1, "latency_ms": 7321.4, "usd": 0.000421, "model_version": "gemini-2.5-pro", "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": 1.0, "latency_ms_mean": 7815.5, "usd_sum": 0.001263 } }, { "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": "4", "compliant": true, "score": 0.6667, "detail": { "predicted": 4.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 10444.2, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 10636.4, "usd": 0.000474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 371, "output_tokens": 1, "latency_ms": 11993.0, "usd": 0.000474, "model_version": "gemini-2.5-pro", "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": 371.0, "output_tokens_mean": 1.0, "latency_ms_mean": 11024.533, "usd_sum": 0.001422 } }, { "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": "```json\n{\n \"sweet\": 1.5,\n \"sour\": 8.0,\n \"salty\": 7.0,\n \"bitter\": 0.5,\n \"umami\": 7.5\n}\n```", "compliant": true, "score": 0.6, "detail": { "per_key": { "sweet": { "predicted": 1.5, "expected": 1.0, "score": 0.75 }, "sour": { "predicted": 8.0, "expected": 7.0, "score": 0.5 }, "salty": { "predicted": 7.0, "expected": 6.0, "score": 0.5 }, "bitter": { "predicted": 0.5, "expected": 1.5, "score": 0.5 }, "umami": { "predicted": 7.5, "expected": 7.0, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 370, "output_tokens": 60, "latency_ms": 9604.2, "usd": 0.001063, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"sweet\": 1.5,\n \"sour\": 8.0,\n \"salty\": 7.5,\n \"bitter\": 0.5,\n \"umami\": 6.5\n}\n```", "compliant": true, "score": 0.55, "detail": { "per_key": { "sweet": { "predicted": 1.5, "expected": 1.0, "score": 0.75 }, "sour": { "predicted": 8.0, "expected": 7.0, "score": 0.5 }, "salty": { "predicted": 7.5, "expected": 6.0, "score": 0.25 }, "bitter": { "predicted": 0.5, "expected": 1.5, "score": 0.5 }, "umami": { "predicted": 6.5, "expected": 7.0, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 370, "output_tokens": 60, "latency_ms": 8725.3, "usd": 0.001063, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"sweet\": 1.5,\n \"sour\": 8.5,\n \"salty\": 7.5,\n \"bitter\": 1.0,\n \"umami\": 6.0\n}\n```", "compliant": true, "score": 0.5, "detail": { "per_key": { "sweet": { "predicted": 1.5, "expected": 1.0, "score": 0.75 }, "sour": { "predicted": 8.5, "expected": 7.0, "score": 0.25 }, "salty": { "predicted": 7.5, "expected": 6.0, "score": 0.25 }, "bitter": { "predicted": 1.0, "expected": 1.5, "score": 0.75 }, "umami": { "predicted": 6.0, "expected": 7.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 370, "output_tokens": 60, "latency_ms": 10444.4, "usd": 0.001063, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.55, "score_summary": { "mean": 0.55, "stdev": 0.05, "sem": 0.0289, "ci95_lo": 0.4934, "ci95_hi": 0.6066, "n": 3 }, "score_if_valid": 0.55, "format_rate": 1.0, "metrics": { "input_tokens_mean": 370.0, "output_tokens_mean": 60.0, "latency_ms_mean": 9591.3, "usd_sum": 0.003189 } }, { "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", "compliant": true, "score": 0.6667, "detail": { "predicted": 2.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 362, "output_tokens": 1, "latency_ms": 6448.5, "usd": 0.000463, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "2.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 2.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 362, "output_tokens": 3, "latency_ms": 9830.6, "usd": 0.000483, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "2.0", "compliant": true, "score": 0.6667, "detail": { "predicted": 2.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 362, "output_tokens": 3, "latency_ms": 11263.8, "usd": 0.000483, "model_version": "gemini-2.5-pro", "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": 362.0, "output_tokens_mean": 2.333, "latency_ms_mean": 9180.967, "usd_sum": 0.001429 } }, { "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": "```json\n{\n \"id\": \"ogs:core:ingredient:fleur-de-sel\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"fr\": \"Fleur de sel\",\n \"en\": \"Fleur de sel\"\n },\n \"primary_language\": \"fr\",\n \"available_languages\": [\n \"fr\",\n \"en\"\n ],\n \"category\": \"salt\",\n \"subcategory\": \"Finishing sea salt\",\n \"description\": {\n \"en\": \"Fleur de sel ('flower of salt' in French) is a delicate, flaky sea salt harvested by hand from the thin top layer of salt ponds. Prized for its high mineral content, subtle flavor, and crunchy texture, it is an ideal finishing salt.\",\n \"fr\": \"La fleur de sel est un sel marin délicat et floconneux, récolté à la main sur la fine couche supérieure des marais salants. Appréciée pour sa haute teneur en minéraux, sa saveur subtile et sa texture croquante, elle est un sel de finition idéal.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"salty\": 9.5,\n \"bitter\": 1.0,\n \"sweet\": 0.5\n },\n \"structural\": {\n \"astringency\": 1.0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"oceanic\",\n \"item\": \"brine\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"delicate\",\n \"crunchy\",\n \"flaky\",\n \"crystalline\"\n ],\n \"finish_length\": 6.0,\n \"complexity\": 5.0\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Guérande, France\",\n \"fr\": \"Guérande, France\"\n },\n \"terroir_notes\": {\n \"en\": \"Hand-harvested from the thin, crystalline top layer of salt evaporation ponds. Its character is influenced by the mineral composition of the local clay beds and seawater.\",\n \"fr\": \"Récoltée à la main sur la fine couche cristalline supérieure des bassins d'évaporation. Son caractère est influencé par la composition minérale des fonds argileux locaux et de l'eau de mer.\"\n }\n },\n \"notes\": {\n \"en\": \"Best used as a finishing salt to preserve its delicate crystal structure. Sprinkle on salads, grilled meats, vegetables, or even desserts like caramel and chocolate.\"\n }\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": 2915, "output_tokens": 629, "latency_ms": 27812.3, "usd": 0.009934, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:fleur-de-sel\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Fleur de sel\",\n \"primary_language\": \"en\",\n \"category\": \"salt\",\n \"description\": {\n \"en\": \"Fleur de sel ('flower of salt' in French) is a hand-harvested sea salt known for its delicate flavor, high moisture content, and flaky texture. It is typically used as a finishing salt.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 0,\n \"salty\": 8.0,\n \"bitter\": 0.5,\n \"umami\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"oceanic\",\n \"item\": \"sea breeze\",\n \"intensity\": 1.5\n }\n ],\n \"texture\": [\n \"flaky\",\n \"crystalline\",\n \"crunchy\",\n \"delicate\"\n ],\n \"finish_length\": 4,\n \"complexity\": 2\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Coastal salt pans, famously from Guérande, France.\"\n },\n \"terroir_notes\": {\n \"en\": \"Harvested from the top layer of salt ponds, giving it a high moisture content and distinct mineral complexity from the local environment.\"\n }\n }\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": 2915, "output_tokens": 378, "latency_ms": 13118.4, "usd": 0.007424, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:fleur-de-sel\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Fleur de sel\",\n \"fr\": \"Fleur de sel\"\n },\n \"category\": \"salt\",\n \"description\": {\n \"en\": \"Fleur de sel ('flower of salt' in French) is a delicate, hand-harvested sea salt that forms a thin, crystalline crust on the surface of seawater. It is prized for its clean, briny flavor, high mineral content, and flaky texture.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"salty\": 9.5,\n \"bitter\": 1,\n \"sweet\": 0,\n \"sour\": 0,\n \"umami\": 0.5\n },\n \"structural\": {\n \"astringency\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"oceanic\",\n \"item\": \"sea breeze\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"crystalline\",\n \"flaky\",\n \"delicate\",\n \"moist\",\n \"crunchy\"\n ],\n \"finish_length\": 6,\n \"complexity\": 3\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Coastal salt marshes, famously from Guérande, France, but also produced in Spain, Portugal, and other regions.\"\n },\n \"season\": {\n \"en\": \"Summer\"\n },\n \"terroir_notes\": {\n \"en\": \"Harvested from the top layer of salt evaporation ponds, influenced by sun, wind, and the local mineralogy of the clay pans. This gives it a unique character and higher moisture content than other salts.\"\n }\n }\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": 2915, "output_tokens": 466, "latency_ms": 16446.1, "usd": 0.008304, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2915.0, "output_tokens_mean": 491.0, "latency_ms_mean": 19125.6, "usd_sum": 0.025662 } }, { "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": "```json\n{\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\": {\n \"en\": \"Loire Valley\"\n },\n \"appellation\": {\n \"en\": \"Sancerre\"\n },\n \"abv\": 13.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1,\n \"sour\": 8,\n \"salty\": 0.5,\n \"bitter\": 2,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 8,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 4,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"berry\",\n \"item\": \"gooseberry\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"grapefruit\",\n \"qualifier\": \"zest\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"flint\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"herbaceous\",\n \"item\": \"cut grass\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"passion fruit\",\n \"intensity\": 3\n }\n ],\n \"finish_length\": 6,\n \"complexity\": 5\n },\n \"notes\": {\n \"en\": \"A generic profile for a classic Sancerre, characterized by high acidity, pronounced minerality (flint), and aromas of gooseberry, citrus, and grass.\"\n }\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": 2927, "output_tokens": 592, "latency_ms": 14661.0, "usd": 0.009579, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:sancerre-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Sancerre\",\n \"type\": \"wine\",\n \"grape_varieties\": [\n \"Sauvignon Blanc\"\n ],\n \"region\": {\n \"en\": \"Loire Valley\"\n },\n \"appellation\": {\n \"en\": \"Sancerre\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.0,\n \"sour\": 8.0,\n \"salty\": 1.5,\n \"bitter\": 2.0,\n \"umami\": 0.5\n },\n \"structural\": {\n \"body\": 3.0,\n \"acidity_perception\": 8.0,\n \"tannin\": 0.0,\n \"astringency\": 1.0,\n \"alcohol_heat\": 4.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"berry\",\n \"item\": \"gooseberry\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"grapefruit\",\n \"intensity\": 7.0\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"flint\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herbaceous\",\n \"item\": \"cut grass\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"zest\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"elderflower\",\n \"intensity\": 4.0\n }\n ],\n \"finish_length\": 6.0,\n \"complexity\": 5.0\n }\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": 2927, "output_tokens": 561, "latency_ms": 18483.8, "usd": 0.009269, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:sancerre-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Sancerre\",\n \"type\": \"wine\",\n \"subtype\": \"White Wine\",\n \"grape_varieties\": [\n \"Sauvignon Blanc\"\n ],\n \"region\": \"Loire Valley\",\n \"appellation\": \"Sancerre\",\n \"abv\": 13.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 8.0,\n \"salty\": 1.0,\n \"bitter\": 2.0,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3.5,\n \"acidity_perception\": 8.0,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 4.0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"berry\",\n \"item\": \"gooseberry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"grapefruit\",\n \"qualifier\": \"zest\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"green\",\n \"item\": \"cut grass\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"flint\",\n \"intensity\": 5.5\n }\n ],\n \"finish_length\": 6.5,\n \"complexity\": 7.0\n },\n \"notes\": \"A generic profile for a Sancerre wine, known for its high acidity, light body, and characteristic aromas of gooseberry, citrus, and a distinctive flinty minerality from the region's terroir.\"\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": 2927, "output_tokens": 574, "latency_ms": 13901.6, "usd": 0.009399, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2927.0, "output_tokens_mean": 575.667, "latency_ms_mean": 15682.133, "usd_sum": 0.028247 } }, { "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": "```json\n{\n \"id\": \"ogs:example:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Brie on Baguette with Brut Champagne\"\n },\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\": 96,\n \"primary\": true,\n \"description\": {\n \"en\": \"The effervescence and high acidity of the Champagne effectively cleanse the palate from the rich, creamy cheese.\"\n }\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 92,\n \"description\": {\n \"en\": \"The beverage's crisp acidity provides a structural counterpoint to the fat and richness of the Brie.\"\n }\n },\n {\n \"type\": \"contrast\",\n \"score\": 88,\n \"description\": {\n \"en\": \"There is a textural contrast between the creamy, soft cheese and the sharp, crisp bubbles of the Champagne.\"\n }\n }\n ],\n \"overall_score\": 93,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.5,\n \"detail\": {\n \"en\": \"The carbonation is the primary mechanism for refreshing the palate after each bite of rich cheese.\"\n }\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.3,\n \"detail\": {\n \"en\": \"High acidity cuts through the fat of the brie, preventing palate fatigue.\"\n }\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.2,\n \"detail\": {\n \"en\": \"The acidity of the wine balances the richness of the cheese, creating a harmonious mouthfeel.\"\n }\n }\n ],\n \"confidence\": 0.95,\n \"notes\": {\n \"en\": \"This is a quintessential example of a palate-cleansing pairing, where the beverage's structure is used to counteract the richness of the food.\"\n }\n}\n```", "compliant": true, "score": 0.5, "detail": { "schema_valid": true, "schema_errors": [], "consistent": false, "required_fields": { "id": { "predicted": "ogs:example:pairing:brie-champagne", "expected": "ogs:core:pairing:brie-champagne", "match": false }, "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": 3843, "output_tokens": 574, "latency_ms": 17520.2, "usd": 0.010544, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": {\n \"en\": \"Brie with Champagne\"\n },\n \"description\": {\n \"en\": \"A classic pairing where the high acidity and effervescence of Brut Champagne cut through the rich, creamy texture of Brie, cleansing the palate with each sip.\"\n },\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\": {\n \"en\": \"The Champagne's effervescence and acidity effectively cleanse the palate from the rich creaminess of the Brie.\"\n }\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 90,\n \"description\": {\n \"en\": \"The high acidity of the wine provides an excellent counterpoint to the fat content of the cheese.\"\n }\n },\n {\n \"type\": \"contrast\",\n \"score\": 88,\n \"description\": {\n \"en\": \"The crisp texture and lean body of the Champagne contrasts beautifully with the soft, creamy mouthfeel of the Brie.\"\n }\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 82\n }\n ],\n \"overall_score\": 93,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.4\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.3\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.2\n },\n {\n \"code\": \"CONTRAST_RICH_CRISP\",\n \"weight\": 0.1\n }\n ],\n \"confidence\": 0.95,\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"notes\": {\n \"en\": \"This is a widely recognized and classic pairing in gastronomy.\"\n }\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:brie-champagne", "expected": "ogs:core:pairing:brie-champagne", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:brie-on-baguette", "expected": "ogs:core:dish:brie-on-baguette", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:brut-champagne-nv", "expected": "ogs:core:beverage:brut-champagne-nv", "match": true } } }, "metrics": { "input_tokens": 3843, "output_tokens": 584, "latency_ms": 14798.1, "usd": 0.010644, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie with Brut 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\": \"The high acidity and effervescence of the Champagne cut through the creaminess of the Brie, cleansing the palate.\"\n },\n {\n \"type\": \"contrast\",\n \"score\": 90,\n \"description\": \"A classic rich-crisp contrast; the rich, fatty cheese is balanced by the lean, crisp beverage.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 88,\n \"description\": \"The Champagne's acidity provides excellent structural balance to the fat content of the Brie.\"\n }\n ],\n \"overall_score\": 93,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.9,\n \"detail\": \"Carbonation physically scrubs the palate of the rich, creamy brie.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.9,\n \"detail\": \"High acidity in the Champagne refreshes the palate from the brie's fat.\"\n },\n {\n \"code\": \"CONTRAST_RICH_CRISP\",\n \"weight\": 0.8,\n \"detail\": \"The rich, creamy texture of the brie is contrasted by the crisp, lean body of the Champagne.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.7,\n \"detail\": \"The beverage's acidity effectively cuts through the richness of the cheese, creating freshness.\"\n }\n ],\n \"confidence\": 0.95,\n \"notes\": \"A quintessential example of a palate-cleansing pairing where the beverage's structure is used to counteract the richness of the food.\"\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:brie-champagne", "expected": "ogs:core:pairing:brie-champagne", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:brie-on-baguette", "expected": "ogs:core:dish:brie-on-baguette", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:brut-champagne-nv", "expected": "ogs:core:beverage:brut-champagne-nv", "match": true } } }, "metrics": { "input_tokens": 3843, "output_tokens": 549, "latency_ms": 9933.8, "usd": 0.010294, "model_version": "gemini-2.5-pro", "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": 3843.0, "output_tokens_mean": 569.0, "latency_ms_mean": 14084.033, "usd_sum": 0.031482 } }, { "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": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 8.5,\n \"sour\": 2.5,\n \"salty\": 0.0,\n \"bitter\": 0.0,\n \"umami\": 0.0\n },\n \"structural\": {\n \"body\": 6.5,\n \"acidity_perception\": 2.5,\n \"tannin\": 0.0,\n \"astringency\": 0.0,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"mango\",\n \"intensity\": 9.0\n },\n {\n \"family\": \"confection\",\n \"group\": \"sugar\",\n \"item\": \"honey\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"peach\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"tropical flower\",\n \"item\": \"jasmine\",\n \"intensity\": 3.0\n },\n {\n \"family\": \"spice\",\n \"group\": \"warm spice\",\n \"item\": \"saffron\",\n \"intensity\": 2.5\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.5, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 6.5, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0.0, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 771, "output_tokens": 362, "latency_ms": 16762.1, "usd": 0.004584, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 8.0,\n \"sour\": 2.5,\n \"salty\": 0.0,\n \"bitter\": 0.5,\n \"umami\": 0.0\n },\n \"structural\": {\n \"body\": 7.0,\n \"acidity_perception\": 2.5,\n \"tannin\": 0.0,\n \"astringency\": 0.0,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"mango\",\n \"intensity\": 9.0\n },\n {\n \"family\": \"confection\",\n \"group\": \"honey\",\n \"item\": \"honey\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone fruit\",\n \"item\": \"apricot\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"jasmine\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"resinous\",\n \"item\": \"pine\",\n \"intensity\": 3.0\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.0, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 7.0, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0.0, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 771, "output_tokens": 364, "latency_ms": 15911.9, "usd": 0.004604, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 8.0,\n \"sour\": 2.5,\n \"salty\": 0.0,\n \"bitter\": 0.0,\n \"umami\": 0.0\n },\n \"structural\": {\n \"body\": 6.0,\n \"acidity_perception\": 2.5,\n \"tannin\": 0.0,\n \"astringency\": 0.5,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tropical\",\n \"item\": \"mango\",\n \"intensity\": 9.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"stone_fruit\",\n \"item\": \"peach\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"sugar\",\n \"item\": \"honey\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"white_flower\",\n \"item\": \"jasmine\",\n \"intensity\": 3.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"orange_peel\",\n \"intensity\": 2.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"resin\",\n \"item\": \"pine\",\n \"intensity\": 2.0\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.0, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 6.0, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0.0, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 771, "output_tokens": 406, "latency_ms": 12324.9, "usd": 0.005024, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 771.0, "output_tokens_mean": 377.333, "latency_ms_mean": 14999.633, "usd_sum": 0.014212 } }, { "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": "```json\n{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"fr\",\n \"available_languages\": [\n \"fr\",\n \"en\"\n ],\n \"name\": {\n \"fr\": \"Moules Marinières\",\n \"en\": \"Sailor-Style Mussels\"\n },\n \"description\": {\n \"en\": \"A classic French dish of mussels steamed in a broth of white wine, shallots, parsley, and butter.\",\n \"fr\": \"Un plat classique français de moules cuites à la vapeur dans un bouillon de vin blanc, d'échalotes, de persil et de beurre.\"\n },\n \"cuisine\": \"french\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:mussel\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:black-pepper\",\n \"proportion\": \"trace\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 4,\n \"salty\": 7,\n \"bitter\": 1,\n \"umami\": 5\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 4\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh herbs\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"intensity\": 4\n },\n {\n \"family\": \"dairy\",\n \"group\": \"cream\",\n \"item\": \"butter\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"tender\",\n \"chewy\",\n \"liquid\",\n \"creamy\"\n ],\n \"finish_length\": 5,\n \"complexity\": 6\n }\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": 3558, "output_tokens": 875, "latency_ms": 23347.4, "usd": 0.013198, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\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 },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:black-pepper\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"trace\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.0,\n \"sour\": 4.0,\n \"salty\": 7.0,\n \"bitter\": 1.0,\n \"umami\": 6.0\n },\n \"structural\": {\n \"body\": 4.0,\n \"acidity_perception\": 4.0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh_herb\",\n \"item\": \"parsley\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"brothy\",\n \"tender\",\n \"chewy\"\n ],\n \"finish_length\": 6.0,\n \"complexity\": 5.0\n }\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": 3558, "output_tokens": 732, "latency_ms": 14199.5, "usd": 0.011768, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\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 },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"proportion\": \"significant\",\n \"reduction_level\": 2\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:black-pepper\",\n \"proportion\": \"trace\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 4.0,\n \"salty\": 7.0,\n \"bitter\": 0.5,\n \"umami\": 6.5\n },\n \"structural\": {\n \"body\": 3.0,\n \"acidity_perception\": 4.0\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh-green\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"tree-fruit\",\n \"item\": \"green-apple\",\n \"qualifier\": \"fermented\",\n \"intensity\": 3.0\n }\n ],\n \"texture\": [\n \"chewy\",\n \"tender\",\n \"liquid\",\n \"smooth\"\n ],\n \"finish_length\": 6.0,\n \"complexity\": 5.0\n }\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": 3558, "output_tokens": 798, "latency_ms": 14669.1, "usd": 0.012427, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3558.0, "output_tokens_mean": 801.667, "latency_ms_mean": 17405.333, "usd_sum": 0.037393 } }, { "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": "```json\n{\n \"id\": \"ogs:core:ingredient:saffron-stigma\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"saffron\"\n },\n \"category\": \"spice\",\n \"subcategory\": \"flower stigma\",\n \"description\": {\n \"en\": \"Saffron is a spice derived from the flower of Crocus sativus, commonly known as the 'saffron crocus'. The vivid crimson stigma and styles, called threads, are collected and dried for use mainly as a seasoning and colouring agent in food.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 6,\n \"umami\": 0.5\n },\n \"structural\": {\n \"astringency\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"floral\",\n \"group\": \"dried flower\",\n \"item\": \"saffron\",\n \"intensity\": 8\n },\n {\n \"family\": \"herbal\",\n \"group\": \"dried herb\",\n \"item\": \"hay\",\n \"intensity\": 7\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"iodine\",\n \"intensity\": 5\n },\n {\n \"family\": \"confection\",\n \"group\": \"sugar\",\n \"item\": \"honey\",\n \"intensity\": 4\n }\n ],\n \"finish_length\": 7,\n \"complexity\": 8\n }\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": 2898, "output_tokens": 412, "latency_ms": 15585.7, "usd": 0.007743, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:saffron-stigma\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"saffron\"\n },\n \"category\": \"spice\",\n \"description\": {\n \"en\": \"Saffron is a spice derived from the flower of Crocus sativus, known as the 'saffron crocus'. The vivid crimson stigmas and styles, called threads, are collected and dried for use as a seasoning and colouring agent, prized for its bitter taste, hay-like fragrance, and intense color.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"bitter\": 6,\n \"umami\": 1\n },\n \"structural\": {\n \"astringency\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"dried herbs\",\n \"item\": \"hay\",\n \"intensity\": 8\n },\n {\n \"family\": \"floral\",\n \"group\": \"sweet floral\",\n \"item\": \"honeysuckle\",\n \"intensity\": 5\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"metallic\",\n \"intensity\": 4\n }\n ],\n \"finish_length\": 8.5,\n \"complexity\": 9\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Iran, Spain, India (Kashmir), Greece, Morocco\"\n },\n \"season\": {\n \"en\": \"Autumn\"\n }\n }\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": 2898, "output_tokens": 411, "latency_ms": 15628.7, "usd": 0.007732, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:saffron-stigma\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": {\n \"en\": \"Saffron\"\n },\n \"category\": \"spice\",\n \"description\": {\n \"en\": \"Spice derived from the dried stigma of the Crocus sativus flower, known for its distinct flavor, aroma, and intense golden-yellow color.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 6,\n \"umami\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"dried grass\",\n \"item\": \"hay\",\n \"intensity\": 8\n },\n {\n \"family\": \"confection\",\n \"group\": \"syrup\",\n \"item\": \"honey\",\n \"intensity\": 5\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"metallic\",\n \"intensity\": 4\n }\n ],\n \"finish_length\": 8,\n \"complexity\": 9\n }\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": 2898, "output_tokens": 330, "latency_ms": 13016.9, "usd": 0.006922, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2898.0, "output_tokens_mean": 384.333, "latency_ms_mean": 14743.767, "usd_sum": 0.022397 } }, { "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": "```json\n{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Miso (Red)\"\n },\n \"category\": \"legume\",\n \"subcategory\": \"Fermented soybean paste\",\n \"description\": {\n \"en\": \"Red miso (aka miso) is a type of Japanese fermented soybean paste. It is fermented for a longer period than white or yellow miso, resulting in a deeper, reddish-brown color and a more intense, saltier, and umami-rich flavor profile. It often includes barley or other grains in addition to soybeans and koji.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.0,\n \"sour\": 2.0,\n \"salty\": 8.5,\n \"bitter\": 1.5,\n \"umami\": 9.0\n },\n \"structural\": {\n \"body\": 6.0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"damp earth\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"savory\",\n \"group\": \"roasted\",\n \"item\": \"malty\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"pasty\",\n \"thick\",\n \"grainy\"\n ],\n \"finish_length\": 8.0,\n \"complexity\": 7.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Japan\"\n }\n }\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": "legume", "expected": "other", "match": false } } }, "metrics": { "input_tokens": 2901, "output_tokens": 462, "latency_ms": 18476.6, "usd": 0.008246, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"ja\",\n \"available_languages\": [\n \"ja\",\n \"en\"\n ],\n \"name\": {\n \"primary_language\": \"ja\",\n \"labels\": [\n {\n \"value\": \"赤味噌\",\n \"language\": \"ja\",\n \"script\": \"Jpan\",\n \"role\": \"preferred\"\n },\n {\n \"value\": \"Aka Miso\",\n \"language\": \"ja\",\n \"role\": \"transliteration\",\n \"transliteration_scheme\": \"hepburn-revised\"\n },\n {\n \"value\": \"Red Miso\",\n \"language\": \"en\",\n \"role\": \"preferred\"\n },\n {\n \"value\": \"miso (red)\",\n \"language\": \"en\",\n \"role\": \"alternate\"\n }\n ]\n },\n \"description\": {\n \"en\": \"Aka Miso, or red miso, is a type of Japanese fermented soybean paste. It undergoes a longer fermentation period than lighter varieties like white miso, resulting in a darker reddish-brown color and a deeper, more intense, and saltier flavor profile. It's rich in umami and is commonly used in hearty soups, marinades, and glazes.\"\n },\n \"category\": \"other\",\n \"subcategory\": \"fermented soybean paste\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 2.0,\n \"salty\": 8.5,\n \"bitter\": 1.0,\n \"umami\": 9.0\n },\n \"structural\": {\n \"body\": 7.0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"umami\",\n \"item\": \"dried mushroom\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"savory\",\n \"group\": \"malty\",\n \"item\": \"marmite\",\n \"intensity\": 7.0\n }\n ],\n \"texture\": [\n \"pasty\",\n \"thick\",\n \"grainy\"\n ],\n \"finish_length\": 8.0,\n \"complexity\": 7.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Japan\"\n }\n }\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": 2901, "output_tokens": 665, "latency_ms": 21128.8, "usd": 0.010276, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"available_languages\": [\n \"en\",\n \"ja\"\n ],\n \"name\": {\n \"en\": \"miso (red)\",\n \"ja\": \"赤味噌\"\n },\n \"description\": {\n \"en\": \"Red miso (aka miso) is a type of Japanese fermented soybean paste with a long fermentation period, typically over a year. This results in a dark reddish-brown color and a deep, salty, and umami-rich flavor with earthy and malty notes. It is used in hearty soups, marinades, and glazes.\"\n },\n \"category\": \"protein\",\n \"subcategory\": \"fermented soybean paste\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"salty\": 8.5,\n \"umami\": 8.0,\n \"sweet\": 1.5,\n \"sour\": 1.0,\n \"bitter\": 1.0\n },\n \"structural\": {\n \"body\": 7.0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"earth\",\n \"group\": \"funk\",\n \"item\": \"earthy\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramelized\",\n \"item\": \"malty\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"pasty\",\n \"thick\",\n \"slightly grainy\"\n ],\n \"finish_length\": 8.0,\n \"complexity\": 8.0\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Japan\"\n }\n }\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": 2901, "output_tokens": 502, "latency_ms": 15319.1, "usd": 0.008646, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.2887, "sem": 0.1667, "ci95_lo": 0.34, "ci95_hi": 0.9933, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2901.0, "output_tokens_mean": 543.0, "latency_ms_mean": 18308.167, "usd_sum": 0.027168 } }, { "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": "```json\n{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Urfa chili\",\n \"tr\": \"Urfa Biber\"\n },\n \"primary_language\": \"tr\",\n \"available_languages\": [\n \"en\",\n \"tr\"\n ],\n \"category\": \"spice\",\n \"subcategory\": \"dried chili pepper\",\n \"description\": {\n \"en\": \"A dried Turkish chili pepper of the species Capsicum annuum, cultivated in the Urfa region of Turkey. It is distinctive for its dark, purplish-black color, oily texture, and complex flavor profile that combines earthiness, smokiness, and notes of raisin and chocolate with a mild, building heat.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 1,\n \"salty\": 3,\n \"bitter\": 2.5,\n \"umami\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"wood\",\n \"group\": \"smoke\",\n \"item\": \"smoke\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"qualifier\": \"dried\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"earthy\",\n \"intensity\": 5\n },\n {\n \"family\": \"confection\",\n \"group\": \"chocolate\",\n \"item\": \"dark chocolate\",\n \"intensity\": 4\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"cured\",\n \"item\": \"tobacco\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"oily\",\n \"flaky\",\n \"moist\"\n ],\n \"finish_length\": 6,\n \"complexity\": 7\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Şanlıurfa, Turkey\",\n \"tr\": \"Şanlıurfa, Türkiye\"\n },\n \"terroir_notes\": {\n \"en\": \"Grown in the hot, dry climate of southeastern Anatolia. The peppers undergo a unique two-part curing process ('sweating'), where they are sun-dried during the day and wrapped tightly at night, which preserves their natural oils and develops their deep color and complex flavor.\"\n }\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:urfa-biber", "expected": "ogs:core:ingredient:urfa-biber", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2900, "output_tokens": 641, "latency_ms": 17385.6, "usd": 0.010035, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"labels\": [\n {\n \"value\": \"Urfa Biber\",\n \"language\": \"tr\",\n \"role\": \"preferred\"\n },\n {\n \"value\": \"Urfa chili\",\n \"language\": \"en\",\n \"role\": \"alternate\"\n },\n {\n \"value\": \"Isot pepper\",\n \"language\": \"en\",\n \"role\": \"alternate\"\n }\n ]\n },\n \"primary_language\": \"tr\",\n \"available_languages\": [\n \"tr\",\n \"en\"\n ],\n \"category\": \"spice\",\n \"subcategory\": \"Dried chili pepper\",\n \"description\": {\n \"en\": \"A dried Turkish chili pepper from the Şanlıurfa region. It has a dark, purplish-black color and a complex flavor that is smoky, earthy, and slightly sweet with notes of raisin, coffee, and tobacco. It provides a mild, building heat.\",\n \"tr\": \"Şanlıurfa bölgesinden gelen kurutulmuş bir Türk biberidir. Koyu, morumsu-siyah bir renge ve kuru üzüm, kahve ve tütün notalarıyla dumanlı, topraksı ve hafif tatlı karmaşık bir lezzete sahiptir. Hafif ve giderek artan bir acılık sağlar.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4.5,\n \"sour\": 1.0,\n \"salty\": 2.0,\n \"bitter\": 1.5,\n \"umami\": 5.0\n },\n \"structural\": {\n \"alcohol_heat\": 3.0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"smoky\",\n \"intensity\": 7.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"qualifier\": \"dried\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"savory\",\n \"group\": \"roasted\",\n \"item\": \"tobacco\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"roasted\",\n \"item\": \"dark chocolate\",\n \"intensity\": 4.0\n }\n ],\n \"finish_length\": 6.0,\n \"complexity\": 7.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Şanlıurfa, Turkey\",\n \"tr\": \"Şanlıurfa, Türkiye\"\n }\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:urfa-biber", "expected": "ogs:core:ingredient:urfa-biber", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2900, "output_tokens": 697, "latency_ms": 17916.8, "usd": 0.010595, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Urfa chili\",\n \"category\": \"spice\",\n \"description\": {\n \"en\": \"A dried Turkish chili pepper, also known as Isot pepper or Urfa Biber. It has a deep, purplish-black color and a complex flavor profile that is smoky, earthy, and sweet with notes of raisin and chocolate. It provides a moderate, slow-building heat.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 6.5,\n \"sour\": 1,\n \"salty\": 1.5,\n \"bitter\": 3,\n \"umami\": 4.5\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"intensity\": 7\n },\n {\n \"family\": \"savory\",\n \"group\": \"smoked\",\n \"item\": \"smoke\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"earthy\",\n \"intensity\": 5\n },\n {\n \"family\": \"confection\",\n \"group\": \"cacao\",\n \"item\": \"dark chocolate\",\n \"intensity\": 4\n },\n {\n \"family\": \"earth\",\n \"group\": \"tobacco\",\n \"item\": \"tobacco\",\n \"intensity\": 3.5\n }\n ],\n \"finish_length\": 7,\n \"complexity\": 8\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Şanlıurfa, Turkey\"\n },\n \"terroir_notes\": {\n \"en\": \"Traditionally prepared by sun-drying the peppers during the day and wrapping them tightly at night. This 'sweating' process preserves the pepper's natural oils, intensifying its flavor and developing its characteristic dark color.\"\n }\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient:urfa-biber", "expected": "ogs:core:ingredient:urfa-biber", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "category": { "predicted": "spice", "expected": "spice", "match": true } } }, "metrics": { "input_tokens": 2900, "output_tokens": 518, "latency_ms": 22821.4, "usd": 0.008805, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2900.0, "output_tokens_mean": 618.667, "latency_ms_mean": 19374.6, "usd_sum": 0.029435 } }, { "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": "```json\n{\n \"id\": \"ogs:core:ingredient:meyer-lemon\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Meyer lemon\"\n },\n \"category\": \"fruit\",\n \"subcategory\": \"citrus\",\n \"description\": {\n \"en\": \"A hybrid citrus fruit native to China, thought to be a cross between a citron and a mandarin/pomelo hybrid. It is sweeter and less acidic than the more common Lisbon or Eureka lemons, with a distinctive floral, slightly spicy aroma.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 7,\n \"salty\": 0,\n \"bitter\": 1,\n \"umami\": 0\n },\n \"structural\": {\n \"acidity_perception\": 7,\n \"astringency\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"zest\",\n \"intensity\": 8\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"jasmine\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh green\",\n \"item\": \"bergamot\",\n \"intensity\": 5\n }\n ],\n \"finish_length\": 6,\n \"complexity\": 6\n },\n \"origin\": {\n \"region\": {\n \"en\": \"China\"\n }\n }\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": 2896, "output_tokens": 411, "latency_ms": 12997.8, "usd": 0.00773, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:meyer-lemon\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Meyer lemon\"\n },\n \"category\": \"fruit\",\n \"subcategory\": \"citrus\",\n \"description\": {\n \"en\": \"A hybrid citrus fruit, known for its thin rind, deep yellow color, and a sweeter, more floral aroma compared to a regular lemon. It's a cross between a citron and a mandarin/pomelo hybrid.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 7.0,\n \"salty\": 0,\n \"bitter\": 1.0,\n \"umami\": 0\n },\n \"structural\": {\n \"acidity_perception\": 7.0,\n \"astringency\": 1.5\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"zest\",\n \"intensity\": 8.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"orange blossom\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"soft herbs\",\n \"item\": \"bergamot\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"juicy\",\n \"thin-skinned\",\n \"tender\"\n ],\n \"finish_length\": 6.5,\n \"complexity\": 6.0\n },\n \"origin\": {\n \"region\": {\n \"en\": \"China\"\n },\n \"season\": {\n \"en\": \"Late fall to early spring\"\n }\n }\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": 2896, "output_tokens": 476, "latency_ms": 11929.7, "usd": 0.00838, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:meyer-lemon\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Meyer lemon\",\n \"category\": \"fruit\",\n \"subcategory\": \"citrus\",\n \"description\": \"A hybrid citrus fruit, believed to be a cross between a citron and a mandarin/pomelo hybrid. Known for its thin, deep yellow-orange skin, lower acidity, and more complex, floral aroma compared to common lemon varieties.\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4.0,\n \"sour\": 7.0,\n \"bitter\": 1.0,\n \"umami\": 0.0\n },\n \"structural\": {\n \"acidity_perception\": 7.0,\n \"astringency\": 1.0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"zest\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"orange blossom\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh green\",\n \"item\": \"bergamot\",\n \"intensity\": 3.0\n }\n ],\n \"texture\": [\n \"juicy\",\n \"pulpy\",\n \"thin-skinned\"\n ],\n \"finish_length\": 5.0,\n \"complexity\": 6.0\n },\n \"origin\": {\n \"region\": \"China\",\n \"season\": \"Winter\"\n }\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": 2896, "output_tokens": 433, "latency_ms": 14254.7, "usd": 0.00795, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2896.0, "output_tokens_mean": 440.0, "latency_ms_mean": 13060.733, "usd_sum": 0.02406 } }, { "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": "```json\n{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Wild Huitlacoche\",\n \"es\": \"Huitlacoche Silvestre\"\n },\n \"primary_language\": \"en\",\n \"available_languages\": [\n \"en\",\n \"es\"\n ],\n \"category\": \"fungus\",\n \"subcategory\": \"corn fungus\",\n \"description\": {\n \"en\": \"A fungus that grows on corn, considered a delicacy in Mexican cuisine. It has a unique earthy, savory, and slightly sweet flavor, often compared to black truffles or mushrooms.\",\n \"es\": \"Un hongo que crece en el maíz, considerado un manjar en la cocina mexicana. Tiene un sabor único terroso, sabroso y ligeramente dulce, a menudo comparado con las trufas negras o los champiñones.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 0,\n \"salty\": 0.5,\n \"bitter\": 1,\n \"umami\": 8\n },\n \"structural\": {\n \"body\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"truffle\",\n \"intensity\": 8\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"grain\",\n \"item\": \"corn\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"savory\",\n \"group\": \"smoke\",\n \"item\": \"smoke\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"soft\",\n \"tender\",\n \"spongy\"\n ],\n \"finish_length\": 6,\n \"complexity\": 7\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Mexico\"\n },\n \"season\": {\n \"en\": \"Summer / Rainy Season\"\n },\n \"terroir_notes\": {\n \"en\": \"Grows on maize (corn) as a pathogenic plant fungus. The flavor is influenced by the variety of corn.\"\n }\n }\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": 2901, "output_tokens": 577, "latency_ms": 18575.5, "usd": 0.009396, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Wild Huitlacoche\",\n \"es\": \"Huitlacoche\"\n },\n \"category\": \"fungus\",\n \"subcategory\": \"Corn fungus\",\n \"description\": {\n \"en\": \"A parasitic fungus that grows on corn cobs, prized as a delicacy in Mexican cuisine. It has a complex, savory flavor that is earthy, smoky, and slightly sweet, often compared to a combination of mushrooms and sweet corn.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.0,\n \"sour\": 0.5,\n \"salty\": 0.5,\n \"bitter\": 1.0,\n \"umami\": 8.5\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"black truffle\",\n \"intensity\": 7.5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"grain\",\n \"item\": \"sweet corn\",\n \"qualifier\": \"cooked\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"wood\",\n \"group\": \"smoke\",\n \"item\": \"smoke\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"soft\",\n \"tender\",\n \"velvety\"\n ],\n \"finish_length\": 6.5,\n \"complexity\": 7.0\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Mexico\"\n },\n \"season\": {\n \"en\": \"Rainy season (May to November)\"\n },\n \"terroir_notes\": {\n \"en\": \"Grows on maize cobs. Flavor is influenced by the host corn variety and local climate conditions.\"\n }\n }\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": 2901, "output_tokens": 500, "latency_ms": 25220.6, "usd": 0.008626, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"wild huitlacoche\"\n },\n \"primary_language\": \"en\",\n \"category\": \"fungus\",\n \"subcategory\": \"Corn fungus\",\n \"description\": {\n \"en\": \"A fungus that grows on corn (maize), considered a delicacy in Mexican cuisine. It has a complex savory, earthy, and slightly sweet flavor, often referred to as 'corn smut' or 'Mexican truffle'.\"\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 0.5,\n \"salty\": 1,\n \"bitter\": 1,\n \"umami\": 8\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"truffle\",\n \"intensity\": 7\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"sweet corn\",\n \"qualifier\": \"cooked\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"damp soil\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\n \"soft\",\n \"spongy\",\n \"tender\",\n \"creamy\"\n ],\n \"finish_length\": 6,\n \"complexity\": 7\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Mexico\"\n },\n \"season\": {\n \"en\": \"Summer rainy season (June to September)\"\n },\n \"terroir_notes\": {\n \"en\": \"Grows parasitically on ears of corn (Zea mays). Flavor is influenced by the variety of host corn and local climate conditions.\"\n }\n },\n \"notes\": {\n \"en\": \"Also known by its Nahuatl name 'cuitlacoche'. It is highly perishable and is often cooked and preserved or sold canned outside of its native region.\"\n }\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": 2901, "output_tokens": 544, "latency_ms": 17295.9, "usd": 0.009066, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2901.0, "output_tokens_mean": 540.333, "latency_ms_mean": 20364.0, "usd_sum": 0.027088 } }, { "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": "```json\n{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Barolo\",\n \"type\": \"wine\",\n \"subtype\": \"Red Wine\",\n \"grape_varieties\": [\n \"Nebbiolo\"\n ],\n \"region\": {\n \"en\": \"Piedmont\"\n },\n \"appellation\": {\n \"en\": \"Barolo DOCG\"\n },\n \"abv\": 14.5,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.0,\n \"sour\": 8.0,\n \"salty\": 0.0,\n \"bitter\": 3.0,\n \"umami\": 0.5\n },\n \"structural\": {\n \"body\": 8.5,\n \"acidity_perception\": 8.0,\n \"tannin\": 9.0,\n \"astringency\": 8.5,\n \"alcohol_heat\": 7.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"cherry\",\n \"intensity\": 7.0\n },\n {\n \"family\": \"floral\",\n \"group\": \"rose\",\n \"item\": \"rose\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"tar\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"licorice\",\n \"intensity\": 5.0\n }\n ],\n \"finish_length\": 8.0,\n \"complexity\": 8.5\n }\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": 2920, "output_tokens": 485, "latency_ms": 17080.5, "usd": 0.0085, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Barolo\",\n \"type\": \"wine\",\n \"subtype\": \"Red Wine\",\n \"grape_varieties\": [\n \"Nebbiolo\"\n ],\n \"region\": {\n \"en\": \"Piedmont\"\n },\n \"appellation\": {\n \"en\": \"Barolo DOCG\"\n },\n \"abv\": 14.5,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 8,\n \"salty\": 0,\n \"bitter\": 7,\n \"umami\": 2\n },\n \"structural\": {\n \"body\": 9,\n \"acidity_perception\": 8.5,\n \"tannin\": 9.5,\n \"astringency\": 9,\n \"alcohol_heat\": 7.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"floral\",\n \"group\": \"rose\",\n \"item\": \"rose\",\n \"qualifier\": \"dried\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"petroleum\",\n \"item\": \"tar\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"red fruit\",\n \"item\": \"cherry\",\n \"intensity\": 6\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"licorice\",\n \"intensity\": 5\n }\n ],\n \"finish_length\": 9,\n \"complexity\": 9\n }\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": 2920, "output_tokens": 469, "latency_ms": 14193.8, "usd": 0.00834, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Barolo\",\n \"type\": \"wine\",\n \"subtype\": \"Red Wine\",\n \"grape_varieties\": [\n \"Nebbiolo\"\n ],\n \"region\": {\n \"en\": \"Piedmont\"\n },\n \"appellation\": {\n \"en\": \"Barolo DOCG\"\n },\n \"abv\": 14.5,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0,\n \"sour\": 8,\n \"salty\": 0,\n \"bitter\": 4,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 9,\n \"acidity_perception\": 8,\n \"tannin\": 9,\n \"astringency\": 8,\n \"alcohol_heat\": 7,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"floral\",\n \"group\": \"rose\",\n \"item\": \"rose\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"red-fruit\",\n \"item\": \"cherry\",\n \"qualifier\": \"dried\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"mineral\",\n \"item\": \"tar\",\n \"intensity\": 6\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking-spice\",\n \"item\": \"licorice\",\n \"intensity\": 5\n }\n ],\n \"finish_length\": 9,\n \"complexity\": 9\n }\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": 2920, "output_tokens": 462, "latency_ms": 15081.6, "usd": 0.00827, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2920.0, "output_tokens_mean": 472.0, "latency_ms_mean": 15451.967, "usd_sum": 0.02511 } }, { "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": "```json\n{\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 Scotch Whisky\",\n \"producer\": \"Ardbeg Distillery\",\n \"region\": \"Islay\",\n \"abv\": 46,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 1,\n \"salty\": 3.5,\n \"bitter\": 4,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 6.5,\n \"acidity_perception\": 1,\n \"tannin\": 2,\n \"astringency\": 2,\n \"alcohol_heat\": 7,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"smoke\",\n \"item\": \"peat\",\n \"intensity\": 9\n },\n {\n \"family\": \"marine\",\n \"group\": \"coastal\",\n \"item\": \"iodine\",\n \"intensity\": 8\n },\n {\n \"family\": \"marine\",\n \"group\": \"coastal\",\n \"item\": \"brine\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"zest\",\n \"intensity\": 5\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"vanilla\",\n \"intensity\": 4\n }\n ],\n \"finish_length\": 8.5,\n \"complexity\": 8\n },\n \"notes\": \"A classic Islay single malt known for its powerful peat smoke, iodine, and maritime character, balanced by underlying citrus and sweetness.\"\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:ardbeg-10-islay", "expected": "ogs:core:beverage:ardbeg-10-islay", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "spirit", "expected": "spirit", "match": true } } }, "metrics": { "input_tokens": 2927, "output_tokens": 505, "latency_ms": 13786.3, "usd": 0.008709, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:ardbeg-10-islay\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Islay single malt\",\n \"type\": \"spirit\",\n \"subtype\": \"Islay Single Malt Scotch Whisky\",\n \"producer\": \"Ardbeg Distillery\",\n \"region\": \"Islay, Scotland\",\n \"abv\": 46.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 3,\n \"bitter\": 4,\n \"umami\": 2.5\n },\n \"structural\": {\n \"body\": 7.5,\n \"acidity_perception\": 1,\n \"tannin\": 2,\n \"astringency\": 1,\n \"alcohol_heat\": 7,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"smoke\",\n \"item\": \"peat smoke\",\n \"intensity\": 9\n },\n {\n \"family\": \"herbal\",\n \"group\": \"medicinal\",\n \"item\": \"iodine\",\n \"intensity\": 8\n },\n {\n \"family\": \"marine\",\n \"group\": \"mineral\",\n \"item\": \"brine\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon peel\",\n \"intensity\": 4\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"charred oak\",\n \"intensity\": 5\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"vanilla\",\n \"intensity\": 5\n }\n ],\n \"finish_length\": 8.5,\n \"complexity\": 8\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:ardbeg-10-islay", "expected": "ogs:core:beverage:ardbeg-10-islay", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "spirit", "expected": "spirit", "match": true } } }, "metrics": { "input_tokens": 2927, "output_tokens": 510, "latency_ms": 15773.5, "usd": 0.008759, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:ardbeg-10-islay\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Islay single malt\",\n \"type\": \"spirit\",\n \"subtype\": \"Scotch Whisky\",\n \"region\": \"Islay\",\n \"producer\": \"Ardbeg Distillery\",\n \"abv\": 46,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 3,\n \"bitter\": 4,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 7,\n \"acidity_perception\": 1,\n \"tannin\": 2,\n \"astringency\": 2,\n \"alcohol_heat\": 8,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"smoke\",\n \"item\": \"peat\",\n \"intensity\": 9\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea\",\n \"item\": \"brine\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon peel\",\n \"intensity\": 3\n }\n ],\n \"finish_length\": 8,\n \"complexity\": 8\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:ardbeg-10-islay", "expected": "ogs:core:beverage:ardbeg-10-islay", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "spirit", "expected": "spirit", "match": true } } }, "metrics": { "input_tokens": 2927, "output_tokens": 377, "latency_ms": 12049.7, "usd": 0.007429, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2927.0, "output_tokens_mean": 464.0, "latency_ms_mean": 13869.833, "usd_sum": 0.024897 } }, { "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": "```json\n{\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 \"description\": \"A premium style of sake made without added distilled alcohol, using rice polished to at least 60% of its original weight. Known for its fruity and floral aromas.\",\n \"abv\": 15.5,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.0,\n \"sour\": 4.0,\n \"salty\": 0,\n \"bitter\": 2.0,\n \"umami\": 5.0\n },\n \"structural\": {\n \"body\": 4.0,\n \"acidity_perception\": 4.0,\n \"alcohol_heat\": 4.0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"melon\",\n \"item\": \"cantaloupe\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"pome\",\n \"item\": \"pear\",\n \"intensity\": 6\n },\n {\n \"family\": \"floral\",\n \"group\": \"white_flower\",\n \"item\": \"jasmine\",\n \"intensity\": 5\n }\n ],\n \"finish_length\": 6,\n \"complexity\": 6\n }\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": 2928, "output_tokens": 387, "latency_ms": 14620.4, "usd": 0.00753, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:junmai-ginjo-generic\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"junmai ginjo sake\",\n \"type\": \"sake\",\n \"subtype\": \"Junmai Ginjo\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 4.0,\n \"salty\": 0.5,\n \"bitter\": 2.0,\n \"umami\": 5.0\n },\n \"structural\": {\n \"body\": 4.5,\n \"acidity_perception\": 4.0,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 4.0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"pome\",\n \"item\": \"green apple\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"melon\",\n \"item\": \"cantaloupe\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"honeysuckle\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"savory\",\n \"group\": \"cereal\",\n \"item\": \"steamed rice\",\n \"intensity\": 5.0\n }\n ],\n \"finish_length\": 6.0,\n \"complexity\": 6.5\n }\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": 2928, "output_tokens": 433, "latency_ms": 13613.8, "usd": 0.00799, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\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\": 3.0,\n \"sour\": 4.5,\n \"salty\": 0,\n \"bitter\": 2.0,\n \"umami\": 6.0\n },\n \"structural\": {\n \"body\": 5.0,\n \"acidity_perception\": 4.5,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 4.0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"pome fruit\",\n \"item\": \"green apple\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"melon\",\n \"item\": \"cantaloupe\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"floral\",\n \"group\": \"white flower\",\n \"item\": \"jasmine\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"savory\",\n \"group\": \"grain\",\n \"item\": \"steamed rice\",\n \"intensity\": 5.5\n }\n ],\n \"finish_length\": 6.0,\n \"complexity\": 6.5\n }\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": 2928, "output_tokens": 421, "latency_ms": 10867.1, "usd": 0.00787, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2928.0, "output_tokens_mean": 413.667, "latency_ms_mean": 13033.767, "usd_sum": 0.02339 } }, { "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": "```json\n{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"type\": \"beer\",\n \"subtype\": \"Märzen\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4.5,\n \"sour\": 1.0,\n \"bitter\": 3.5\n },\n \"structural\": {\n \"body\": 6.0,\n \"acidity_perception\": 1.0,\n \"alcohol_heat\": 2.5,\n \"effervescence\": 5.0\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"baked goods\",\n \"item\": \"toast\",\n \"intensity\": 7.0\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"caramel\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"herbal\",\n \"group\": \"dried herbs\",\n \"item\": \"hay\",\n \"intensity\": 2.0\n }\n ],\n \"finish_length\": 5.0,\n \"complexity\": 4.0\n }\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": 2929, "output_tokens": 338, "latency_ms": 14143.7, "usd": 0.007041, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"type\": \"beer\",\n \"subtype\": \"Märzen\",\n \"abv\": 6.0,\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 5,\n \"sour\": 1,\n \"bitter\": 3.5\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 1.5,\n \"alcohol_heat\": 2,\n \"effervescence\": 5.5\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"baked\",\n \"item\": \"toast\",\n \"intensity\": 7\n },\n {\n \"family\": \"confection\",\n \"group\": \"sugar\",\n \"item\": \"caramel\",\n \"intensity\": 5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"dried_herb\",\n \"item\": \"hay\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"group\": \"warm_spice\",\n \"item\": \"black pepper\",\n \"intensity\": 2\n }\n ],\n \"finish_length\": 5,\n \"complexity\": 4\n }\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": 2929, "output_tokens": 369, "latency_ms": 17358.3, "usd": 0.007351, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"type\": \"beer\",\n \"subtype\": \"Märzen\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 4,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3.5,\n \"umami\": 0.5\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 1.5,\n \"alcohol_heat\": 2.5,\n \"effervescence\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"baked\",\n \"item\": \"toast\",\n \"intensity\": 7\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"caramel\",\n \"intensity\": 5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"herb\",\n \"item\": \"dried herbs\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"clove\",\n \"intensity\": 2\n }\n ],\n \"finish_length\": 6,\n \"complexity\": 5\n }\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": 2929, "output_tokens": 379, "latency_ms": 11441.5, "usd": 0.007451, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2929.0, "output_tokens_mean": 362.0, "latency_ms_mean": 14314.5, "usd_sum": 0.021843 } }, { "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": "```json\n{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Crottin de Chavignol & Sancerre Blanc\"\n },\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"match_types\": [\n {\n \"type\": \"harmony\",\n \"score\": 98,\n \"primary\": true,\n \"description\": {\n \"en\": \"A classic regional pairing from the Loire Valley, where the flavor profiles of the tangy goat cheese and crisp Sauvignon Blanc converge beautifully.\"\n }\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 95,\n \"description\": {\n \"en\": \"The high acidity of the Sancerre cuts through the richness and creamy texture of the cheese, creating a balanced mouthfeel.\"\n }\n },\n {\n \"type\": \"refresh\",\n \"score\": 92,\n \"description\": {\n \"en\": \"The wine's bright acidity and mineral notes effectively cleanse the palate between bites of the dense cheese.\"\n }\n }\n ],\n \"overall_score\": 96,\n \"grade\": \"A+\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 1.0,\n \"detail\": {\n \"en\": \"Both Crottin de Chavignol and Sancerre originate from the same region in the Loire Valley, a textbook example of terroir-driven pairing.\"\n }\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.9,\n \"detail\": {\n \"en\": \"Sancerre's sharp acidity provides a perfect counterpoint to the fat and tangy lactic acid in the goat cheese.\"\n }\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.8\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.7\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.6\n },\n {\n \"code\": \"AROMA_SHARED_HERBAL\",\n \"weight\": 0.5,\n \"detail\": {\n \"en\": \"Herbal and flinty notes in the Sancerre often echo the grassy, pastoral character of the goat cheese.\"\n }\n }\n ],\n \"confidence\": 0.98,\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"notes\": {\n \"en\": \"This is one of the most widely cited and celebrated classic pairings in the wine and cheese world.\"\n }\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:crottin-sancerre", "expected": "ogs:core:pairing:crottin-sancerre", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:crottin-de-chavignol", "expected": "ogs:core:dish:crottin-de-chavignol", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:sancerre-blanc", "expected": "ogs:core:beverage:sancerre-blanc", "match": true } } }, "metrics": { "input_tokens": 3851, "output_tokens": 715, "latency_ms": 13162.7, "usd": 0.011964, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Crottin de Chavignol with Sancerre\"\n },\n \"description\": {\n \"en\": \"A classic regional pairing from the Loire Valley, where the crisp acidity and mineral notes of Sancerre beautifully complement the tangy, earthy character of fresh goat cheese.\"\n },\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"match_types\": [\n {\n \"type\": \"harmony\",\n \"score\": 95,\n \"description\": {\n \"en\": \"Classic regional pairing from the Loire Valley, reflecting shared terroir.\"\n },\n \"primary\": true\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 92,\n \"description\": {\n \"en\": \"The wine's high acidity cuts through the cheese's fat and matches its tanginess.\"\n }\n },\n {\n \"type\": \"refresh\",\n \"score\": 88,\n \"description\": {\n \"en\": \"Sancerre's crisp acidity cleanses the palate from the creamy goat cheese.\"\n }\n }\n ],\n \"overall_score\": 93,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.4,\n \"detail\": {\n \"en\": \"Both Sancerre and Crottin de Chavignol originate from the same region in the Loire Valley, a classic example of 'what grows together, goes together'.\"\n }\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.35,\n \"detail\": {\n \"en\": \"The sharp, citrusy acidity of the Sauvignon Blanc cuts through the rich, fatty texture of the goat cheese while complementing its natural tang.\"\n }\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.15,\n \"detail\": {\n \"en\": \"The wine's acidity acts as a palate cleanser, preventing the cheese from becoming cloying.\"\n }\n },\n {\n \"code\": \"AROMA_SHARED_HERBAL\",\n \"weight\": 0.1,\n \"detail\": {\n \"en\": \"Shared grassy and herbal notes in both the wine and cheese create an aromatic bridge.\"\n }\n }\n ],\n \"confidence\": 0.98\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:crottin-sancerre", "expected": "ogs:core:pairing:crottin-sancerre", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:crottin-de-chavignol", "expected": "ogs:core:dish:crottin-de-chavignol", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:sancerre-blanc", "expected": "ogs:core:beverage:sancerre-blanc", "match": true } } }, "metrics": { "input_tokens": 3851, "output_tokens": 659, "latency_ms": 16162.8, "usd": 0.011404, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Crottin de Chavignol with Sancerre\"\n },\n \"description\": {\n \"en\": \"A classic regional pairing from the Loire Valley, where the high acidity and citrus notes of Sancerre perfectly complement the tangy, creamy profile of fresh Crottin de Chavignol goat cheese.\"\n },\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"match_types\": [\n {\n \"type\": \"harmony\",\n \"score\": 98,\n \"primary\": true,\n \"description\": {\n \"en\": \"The shared Loire Valley origin creates a deep, terroir-driven harmony.\"\n }\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 95,\n \"description\": {\n \"en\": \"Sancerre's sharp acidity balances the cheese's rich, fatty texture.\"\n }\n },\n {\n \"type\": \"refresh\",\n \"score\": 92,\n \"description\": {\n \"en\": \"The wine's acidity provides an excellent palate-cleansing effect.\"\n }\n }\n ],\n \"overall_score\": 97,\n \"grade\": \"A+\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 1.0,\n \"detail\": {\n \"en\": \"Both the cheese and the wine are iconic products of the Loire Valley, representing a quintessential regional pairing.\"\n }\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.9,\n \"detail\": {\n \"en\": \"The high acidity of the Sauvignon Blanc cuts through the creamy texture and tangy flavor of the goat cheese, preventing palate fatigue.\"\n }\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.8,\n \"detail\": {\n \"en\": \"The bright citrus (grapefruit, lemon) and mineral notes in the Sancerre mirror and enhance the natural tang of the fresh goat cheese.\"\n }\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.7,\n \"detail\": {\n \"en\": \"The zesty acidity of the Sancerre acts as a powerful palate cleanser between bites of the rich cheese.\"\n }\n }\n ],\n \"confidence\": 0.99\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:crottin-sancerre", "expected": "ogs:core:pairing:crottin-sancerre", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:crottin-de-chavignol", "expected": "ogs:core:dish:crottin-de-chavignol", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:sancerre-blanc", "expected": "ogs:core:beverage:sancerre-blanc", "match": true } } }, "metrics": { "input_tokens": 3851, "output_tokens": 666, "latency_ms": 15773.7, "usd": 0.011474, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3851.0, "output_tokens_mean": 680.0, "latency_ms_mean": 15033.067, "usd_sum": 0.034842 } }, { "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": "```json\n{\n \"id\": \"ogs:core:dish:tonkotsu-ramen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"tonkotsu ramen\",\n \"cuisine\": \"Japanese\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:pork-bone-broth\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:ramen-noodles\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:pork-belly\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:chicken-egg\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:scallion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.0,\n \"sour\": 0.5,\n \"salty\": 7.5,\n \"bitter\": 0.5,\n \"umami\": 9.0\n },\n \"structural\": {\n \"body\": 8.0,\n \"acidity_perception\": 1.0,\n \"astringency\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"animalic\",\n \"item\": \"pork\",\n \"intensity\": 8\n },\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy-sauce\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"creamy\",\n \"chewy\",\n \"tender\",\n \"soft\"\n ],\n \"finish_length\": 8.0,\n \"complexity\": 7.5\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "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": 3558, "output_tokens": 762, "latency_ms": 16907.3, "usd": 0.012068, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:dish:tonkotsu-ramen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Tonkotsu Ramen\"\n },\n \"description\": {\n \"en\": \"A rich and savory Japanese noodle soup featuring a creamy pork bone broth (tonkotsu), wheat noodles, and various toppings such as chashu pork and a soft-boiled egg.\"\n },\n \"cuisine\": \"Japanese\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:tonkotsu-broth\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"dominant\",\n \"notes\": {\n \"en\": \"The rich, emulsified pork bone broth that defines the dish.\"\n }\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:ramen-noodles\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:chashu-pork\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:ajitama-egg\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"significant\",\n \"notes\": {\n \"en\": \"Soft-boiled egg marinated in a soy-based sauce.\"\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:scallion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0.5,\n \"salty\": 7.0,\n \"bitter\": 1.0,\n \"umami\": 9.0\n },\n \"structural\": {\n \"body\": 8.0,\n \"acidity_perception\": 1.0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"cooked_meat\",\n \"item\": \"pork\",\n \"qualifier\": \"cooked\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"garlic\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 4.5\n }\n ],\n \"texture\": [\n \"creamy\",\n \"unctuous\",\n \"chewy\",\n \"tender\",\n \"soft\",\n \"crisp\"\n ],\n \"finish_length\": 8.0,\n \"complexity\": 7.5\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "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": 3558, "output_tokens": 908, "latency_ms": 19588.1, "usd": 0.013527, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:dish:tonkotsu-ramen\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"tonkotsu ramen\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:pork-bone-broth\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:wheat-noodle\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:pork-belly\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:chicken-egg\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori-seaweed\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:scallion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 7,\n \"bitter\": 1,\n \"umami\": 8.5\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"cooked_meat\",\n \"item\": \"pork\",\n \"qualifier\": \"cooked\",\n \"intensity\": 8\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"nori\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"scallion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n },\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soy_sauce\",\n \"intensity\": 6\n }\n ],\n \"finish_length\": 7,\n \"complexity\": 7.5\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "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": 3558, "output_tokens": 712, "latency_ms": 19953.0, "usd": 0.011567, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3558.0, "output_tokens_mean": 794.0, "latency_ms_mean": 18816.133, "usd_sum": 0.037162 } }, { "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": "```json\n{\n \"id\": \"ogs:core:dish:pico-de-gallo\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"es\",\n \"name\": {\n \"es\": \"Pico de Gallo\",\n \"en\": \"Pico de Gallo\"\n },\n \"description\": {\n \"en\": \"A classic Mexican fresh salsa made from chopped tomato, onion, cilantro, fresh jalapeños, salt, and lime juice.\"\n },\n \"cuisine\": \"Mexican\",\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 },\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:onion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:cilantro\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:jalapeno\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:lime-juice\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:salt\",\n \"proportion\": \"accent\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 7,\n \"salty\": 5,\n \"bitter\": 1,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 7\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"leafy\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 8\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"nightshade\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"pepper\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"fresh\",\n \"crisp\",\n \"juicy\",\n \"chunky\"\n ],\n \"finish_length\": 4,\n \"complexity\": 3\n }\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": 3547, "output_tokens": 856, "latency_ms": 15473.6, "usd": 0.012994, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:dish:pico-de-gallo\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Pico de Gallo\",\n \"description\": \"A classic Mexican fresh salsa, also known as salsa fresca, made from chopped tomato, onion, cilantro, fresh jalapeños, salt, and lime juice.\",\n \"cuisine\": \"Mexican\",\n \"course\": \"appetizer\",\n \"service_temperature\": \"cold\",\n \"components\": [\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:roma-tomato\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-onion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:cilantro\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:jalapeno\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:lime-juice\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:salt\",\n \"proportion\": \"trace\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 6,\n \"salty\": 5,\n \"bitter\": 1,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 6\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"solanum\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n },\n {\n \"family\": \"herbal\",\n \"group\": \"fresh herbs\",\n \"item\": \"cilantro\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"intensity\": 4\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"capsicum\",\n \"item\": \"jalapeno\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"crunchy\",\n \"juicy\",\n \"crisp\",\n \"chunky\"\n ],\n \"finish_length\": 4,\n \"complexity\": 3\n }\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": 3547, "output_tokens": 812, "latency_ms": 18424.8, "usd": 0.012554, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:dish:pico-de-gallo\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Pico de Gallo\",\n \"description\": \"A classic fresh Mexican salsa, also known as salsa fresca, made with chopped tomato, onion, cilantro, fresh jalapeños, and lime juice.\",\n \"cuisine\": \"Mexican\",\n \"course\": \"appetizer\",\n \"service_temperature\": \"cool\",\n \"components\": [\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:tomato\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"dominant\"\n },\n {\n \"role\": \"main_vegetable\",\n \"ingredient_ref\": \"ogs:core:ingredient:onion\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:cilantro\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"significant\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:jalapeno\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"acid_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:lime-juice\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:salt\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\"\n }\n ],\n \"overall_sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 6,\n \"salty\": 4,\n \"bitter\": 0.5,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 6\n },\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"fresh herbs\",\n \"item\": \"cilantro\",\n \"qualifier\": \"fresh\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lime\",\n \"qualifier\": \"fresh\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"nightshades\",\n \"item\": \"tomato\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"onion\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"chili pepper\",\n \"item\": \"jalapeño\",\n \"qualifier\": \"fresh\",\n \"intensity\": 4\n }\n ],\n \"texture\": [\n \"crunchy\",\n \"juicy\",\n \"chopped\",\n \"fresh\"\n ],\n \"finish_length\": 3,\n \"complexity\": 3\n }\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": 3547, "output_tokens": 834, "latency_ms": 16009.7, "usd": 0.012774, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3547.0, "output_tokens_mean": 834.0, "latency_ms_mean": 16636.033, "usd_sum": 0.038322 } }, { "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": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 4.0,\n \"sour\": 1.5,\n \"salty\": 7.0,\n \"bitter\": 2.0,\n \"umami\": 8.5\n },\n \"structural\": {\n \"body\": 9.0,\n \"acidity_perception\": 1.5,\n \"tannin\": 0.0,\n \"astringency\": 1.0,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"descriptors\": [\n \"roasted nuts\"\n ],\n \"intensity\": 8.0\n },\n {\n \"family\": \"dairy\",\n \"descriptors\": [\n \"cooked\",\n \"browned butter\"\n ],\n \"intensity\": 7.5\n },\n {\n \"family\": \"savory\",\n \"descriptors\": [\n \"beef broth\"\n ],\n \"intensity\": 7.0\n },\n {\n \"family\": \"confection\",\n \"descriptors\": [\n \"cooked\",\n \"caramel\"\n ],\n \"intensity\": 6.0\n },\n {\n \"family\": \"fruit\",\n \"descriptors\": [\n \"dried\",\n \"apricot\"\n ],\n \"intensity\": 4.0\n },\n {\n \"family\": \"spice\",\n \"descriptors\": [\n \"nutmeg\"\n ],\n \"intensity\": 3.0\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 8.5, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 7.0, "expected": 5.0, "match": true }, "structural.body": { "predicted": 9.0, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 478, "output_tokens": 410, "latency_ms": 15729.7, "usd": 0.004698, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 6.0,\n \"sour\": 2.0,\n \"salty\": 7.0,\n \"bitter\": 2.5,\n \"umami\": 8.5\n },\n \"structural\": {\n \"body\": 8.0,\n \"acidity_perception\": 3.0,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"note\": \"roasted nuts\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"savory\",\n \"note\": \"brown butter\",\n \"intensity\": 7.0\n },\n {\n \"family\": \"confection\",\n \"note\": \"toffee\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"dairy\",\n \"note\": \"cultured cream\",\n \"qualifier\": \"fermented\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"fruit\",\n \"note\": \"apricot\",\n \"qualifier\": \"dried\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"earth\",\n \"note\": \"cellar\",\n \"intensity\": 3.5\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 8.5, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 7.0, "expected": 5.0, "match": true }, "structural.body": { "predicted": 8.0, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 478, "output_tokens": 371, "latency_ms": 12031.2, "usd": 0.004308, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 4.0,\n \"sour\": 1.5,\n \"salty\": 6.5,\n \"bitter\": 1.0,\n \"umami\": 8.0\n },\n \"structural\": {\n \"body\": 8.5,\n \"acidity_perception\": 2.0,\n \"astringency\": 1.5\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"intensity\": 8.5,\n \"notes\": [\n \"toasted nuts\",\n \"brown butter\",\n \"broth\"\n ]\n },\n {\n \"family\": \"dairy\",\n \"intensity\": 7.0,\n \"notes\": [\n \"cooked milk\",\n \"caramel\"\n ]\n },\n {\n \"family\": \"confection\",\n \"intensity\": 5.0,\n \"notes\": [\n \"toffee\",\n \"butterscotch\"\n ]\n },\n {\n \"family\": \"fruit\",\n \"qualifier\": \"dried\",\n \"intensity\": 4.0,\n \"notes\": [\n \"dried apricot\"\n ]\n },\n {\n \"family\": \"spice\",\n \"intensity\": 3.0,\n \"notes\": [\n \"nutmeg\",\n \"white pepper\"\n ]\n },\n {\n \"family\": \"earth\",\n \"intensity\": 2.5,\n \"notes\": [\n \"hay\",\n \"cellar\"\n ]\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 8.0, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 6.5, "expected": 5.0, "match": true }, "structural.body": { "predicted": 8.5, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 478, "output_tokens": 407, "latency_ms": 11698.8, "usd": 0.004667, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 478.0, "output_tokens_mean": 396.0, "latency_ms_mean": 13153.233, "usd_sum": 0.013673 } }, { "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": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 0.0,\n \"salty\": 4.0,\n \"bitter\": 1.5,\n \"umami\": 2.0\n },\n \"structural\": {\n \"body\": 2.0,\n \"acidity_perception\": 0.0,\n \"tannin\": 0.0,\n \"astringency\": 0.0,\n \"alcohol_heat\": 0.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"descriptors\": [\n \"green bell pepper\",\n \"grassy\"\n ],\n \"qualifiers\": [\n \"cooked\"\n ]\n },\n {\n \"family\": \"savory\",\n \"descriptors\": [\n \"smoky\",\n \"charred\"\n ],\n \"qualifiers\": []\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 4.0, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 1.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 2.0, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 467, "output_tokens": 257, "latency_ms": 9670.6, "usd": 0.003154, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 0,\n \"salty\": 4,\n \"bitter\": 2,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 2,\n \"acidity_perception\": 1,\n \"tannin\": 0,\n \"astringency\": 0,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"qualifier\": \"cooked\",\n \"intensity\": 7\n },\n {\n \"family\": \"savory\",\n \"intensity\": 6\n },\n {\n \"family\": \"fruit\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"intensity\": 2\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 4, "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": 467, "output_tokens": 235, "latency_ms": 11059.6, "usd": 0.002934, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 0.5,\n \"salty\": 6.0,\n \"bitter\": 2.5,\n \"umami\": 4.0\n },\n \"structural\": {\n \"body\": 2.0,\n \"acidity_perception\": 0.5,\n \"tannin\": 0.0,\n \"astringency\": 0.0,\n \"alcohol_heat\": 1.0,\n \"effervescence\": 0.0\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"qualifier\": \"cooked\",\n \"notes\": [\n \"green pepper\",\n \"charred\"\n ],\n \"intensity\": 8.5\n },\n {\n \"family\": \"savory\",\n \"notes\": [\n \"smoky\"\n ],\n \"intensity\": 7.0\n },\n {\n \"family\": \"fruit\",\n \"qualifier\": \"fresh\",\n \"notes\": [\n \"bell pepper\"\n ],\n \"intensity\": 3.0\n }\n ]\n}\n```", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 6.0, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 2.0, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 467, "output_tokens": 302, "latency_ms": 14366.5, "usd": 0.003604, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 467.0, "output_tokens_mean": 264.667, "latency_ms_mean": 11698.9, "usd_sum": 0.009692 } }, { "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": "```json\n{\n \"id\": \"ogs:core:pairing:mole-negro-garnacha\",\n \"ogs_version\": \"0.1.0\",\n \"name\": {\n \"en\": \"Mole Negro Enchiladas & Aragonese Garnacha\"\n },\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"intensity_alignment\",\n \"score\": 92,\n \"primary\": true,\n \"description\": {\n \"en\": \"The robust fruit and body of the Garnacha match the high flavor intensity of the complex mole sauce.\"\n }\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 90,\n \"primary\": true,\n \"description\": {\n \"en\": \"The wine's body aligns with the dish's richness, while its fruit balances the chile spice and tannins handle the protein.\"\n }\n },\n {\n \"type\": \"bridge\",\n \"score\": 88,\n \"description\": {\n \"en\": \"An aromatic bridge is formed between the dried fruit notes of the chiles (ancho, pasilla) and the ripe red/dark fruit of the Garnacha.\"\n }\n },\n {\n \"type\": \"harmony\",\n \"score\": 85\n }\n ],\n \"overall_score\": 91,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 1\n },\n {\n \"code\": \"AROMA_SHARED_FRUIT\",\n \"weight\": 0.9\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.8\n },\n {\n \"code\": \"STRUCT_SWEET_OFFSET\",\n \"detail\": {\n \"en\": \"The perceived sweetness of the ripe Garnacha fruit balances the chile heat and slight bitterness from the chocolate.\"\n },\n \"weight\": 0.7\n },\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.6\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_SPICE_ALCOHOL\",\n \"severity\": \"low\",\n \"description\": {\n \"en\": \"A Garnacha with particularly high alcohol could amplify the heat of a very spicy mole to an uncomfortable level.\"\n }\n }\n ],\n \"confidence\": 0.9,\n \"notes\": {\n \"en\": \"A cross-cultural bridge pairing where the ripe dark fruit, full body, and spicy notes of the Aragonese Garnacha stand up to the complex, rich, and spicy chocolate-chile character of the mole negro. The wine's fruitiness complements the dried fruit notes in the chiles, creating a harmonious bridge.\"\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:mole-negro-garnacha", "expected": "ogs:core:pairing:mole-negro-garnacha", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:mole-negro-enchiladas", "expected": "ogs:core:dish:mole-negro-enchiladas", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:garnacha-aragon", "expected": "ogs:core:beverage:garnacha-aragon", "match": true } } }, "metrics": { "input_tokens": 3840, "output_tokens": 727, "latency_ms": 18700.7, "usd": 0.01207, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n{\n \"id\": \"ogs:core:pairing:mole-negro-garnacha\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Mole Negro Enchiladas with Aragonese Garnacha\",\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"structural_balance\",\n \"score\": 95,\n \"primary\": true,\n \"description\": \"The full body of the Garnacha provides an excellent counterpoint to the rich, dense mole sauce.\"\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 93,\n \"primary\": true,\n \"description\": \"Both the complex mole and the robust Garnacha have high flavor intensity, ensuring neither element overpowers the other.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 90,\n \"description\": \"Ripe red fruit flavors in the wine harmonize with the chocolate, nut, and dried fruit notes of the sauce.\"\n },\n {\n \"type\": \"bridge\",\n \"score\": 88,\n \"description\": \"Shared notes of spice and fruit create an aromatic bridge between the dish and beverage.\"\n }\n ],\n \"overall_score\": 92,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.3\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.3\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.2\n },\n {\n \"code\": \"AROMA_SHARED_FRUIT\",\n \"weight\": 0.1\n },\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.1\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_SPICE_ALCOHOL\",\n \"severity\": \"low\",\n \"description\": \"If the mole is exceptionally spicy and the Garnacha has very high alcohol, the alcoholic heat could amplify the chile spice.\",\n \"mitigation\": \"Select a Garnacha with moderate alcohol (under 14.5%) and ensure the dish's spice level is balanced.\"\n }\n ],\n \"confidence\": 0.9,\n \"notes\": \"A powerful, cross-cultural pairing where the ripe fruit, full body, and soft tannins of Aragonese Garnacha successfully stand up to the immense complexity of mole negro. The wine's fruitiness complements the chocolate and chile notes without clashing.\"\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:mole-negro-garnacha", "expected": "ogs:core:pairing:mole-negro-garnacha", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:mole-negro-enchiladas", "expected": "ogs:core:dish:mole-negro-enchiladas", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:garnacha-aragon", "expected": "ogs:core:beverage:garnacha-aragon", "match": true } } }, "metrics": { "input_tokens": 3840, "output_tokens": 674, "latency_ms": 16169.6, "usd": 0.01154, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n{\n \"id\": \"ogs:core:pairing:mole-negro-garnacha\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Mole Negro Enchiladas with Aragonese Garnacha\",\n \"description\": \"A cross-cultural pairing where the ripe, generous fruit and full body of Aragonese Garnacha stand up to the rich, multi-layered chocolate-chile mole sauce. The wine's soft tannins and spicy notes create harmony with the dish's complexity.\",\n \"primary_language\": \"en\",\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"structural_balance\",\n \"score\": 92,\n \"primary\": true,\n \"description\": \"The wine's full body and moderate tannins match the richness of the mole and protein filling.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 90,\n \"description\": \"Ripe fruit flavors in the Garnacha converge with the sweet, savory, and earthy notes of the mole.\"\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 88,\n \"description\": \"Both the dish and beverage have a comparable medium-high intensity, preventing one from overpowering the other.\"\n },\n {\n \"type\": \"bridge\",\n \"score\": 85,\n \"description\": \"Shared spice and earth aromatics create a seamless bridge between the wine and the complex sauce.\"\n }\n ],\n \"overall_score\": 91,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.9,\n \"detail\": \"The full body of the Garnacha aligns perfectly with the weight and richness of the mole sauce and cheese.\"\n },\n {\n \"code\": \"HARMONY_FLAVOR_CONVERGE\",\n \"weight\": 0.9,\n \"detail\": \"Ripe red and black fruit notes in the wine complement the dried fruit, chocolate, and chile flavors of the mole.\"\n },\n {\n \"code\": \"STRUCT_TANNIN_PROTEIN\",\n \"weight\": 0.7,\n \"detail\": \"The wine's soft tannins bind with proteins in the enchilada filling, enhancing the mouthfeel.\"\n },\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.6,\n \"detail\": \"Spicy notes like black pepper in the Garnacha echo the complex spice profile of the chiles in the mole.\"\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.8,\n \"detail\": \"The robust flavor profiles of both the complex mole and the powerful Garnacha are well-matched.\"\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_SPICE_ALCOHOL\",\n \"severity\": \"low\",\n \"description\": \"If the mole is exceptionally spicy, the relatively high alcohol of Garnacha could amplify the heat.\",\n \"mitigation\": \"Pair with a mole that has a balanced, rather than aggressively high, level of spice.\"\n }\n ],\n \"confidence\": 0.95,\n \"evidence\": {\n \"method\": \"expert_panel\"\n }\n}\n```", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:pairing:mole-negro-garnacha", "expected": "ogs:core:pairing:mole-negro-garnacha", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "dish_ref": { "predicted": "ogs:core:dish:mole-negro-enchiladas", "expected": "ogs:core:dish:mole-negro-enchiladas", "match": true }, "beverage_ref": { "predicted": "ogs:core:beverage:garnacha-aragon", "expected": "ogs:core:beverage:garnacha-aragon", "match": true } } }, "metrics": { "input_tokens": 3840, "output_tokens": 828, "latency_ms": 21793.8, "usd": 0.01308, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3840.0, "output_tokens_mean": 743.0, "latency_ms_mean": 18888.033, "usd_sum": 0.03669 } }, { "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": 339, "output_tokens": 1, "latency_ms": 5004.1, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 1, "latency_ms": 6579.7, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 1, "latency_ms": 5605.8, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 339.0, "output_tokens_mean": 1.0, "latency_ms_mean": 5729.867, "usd_sum": 0.001302 } }, { "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": 332, "output_tokens": 1, "latency_ms": 5015.4, "usd": 0.000425, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 1, "latency_ms": 4505.8, "usd": 0.000425, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 332, "output_tokens": 1, "latency_ms": 4505.5, "usd": 0.000425, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 4675.567, "usd_sum": 0.001275 } }, { "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": 333, "output_tokens": 2, "latency_ms": 5322.6, "usd": 0.000436, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 2, "latency_ms": 5902.3, "usd": 0.000436, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 333, "output_tokens": 2, "latency_ms": 6079.1, "usd": 0.000436, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 333.0, "output_tokens_mean": 2.0, "latency_ms_mean": 5768.0, "usd_sum": 0.001308 } }, { "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": 415, "output_tokens": 2, "latency_ms": 7738.5, "usd": 0.000539, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 415, "output_tokens": 2, "latency_ms": 7003.6, "usd": 0.000539, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 415, "output_tokens": 2, "latency_ms": 6554.2, "usd": 0.000539, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 415.0, "output_tokens_mean": 2.0, "latency_ms_mean": 7098.767, "usd_sum": 0.001617 } }, { "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": "bridge", "compliant": true, "score": 1.0, "detail": { "predicted": "bridge", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 330, "output_tokens": 1, "latency_ms": 5420.8, "usd": 0.000423, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "harmony", "compliant": true, "score": 0.0, "detail": { "predicted": "harmony", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 330, "output_tokens": 1, "latency_ms": 7684.1, "usd": 0.000423, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "bridge", "compliant": true, "score": 1.0, "detail": { "predicted": "bridge", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 330, "output_tokens": 1, "latency_ms": 7757.5, "usd": 0.000423, "model_version": "gemini-2.5-pro", "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": 330.0, "output_tokens_mean": 1.0, "latency_ms_mean": 6954.133, "usd_sum": 0.001269 } }, { "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": 368, "output_tokens": 2, "latency_ms": 5975.2, "usd": 0.00048, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 368, "output_tokens": 2, "latency_ms": 7199.8, "usd": 0.00048, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 368, "output_tokens": 2, "latency_ms": 7020.7, "usd": 0.00048, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 368.0, "output_tokens_mean": 2.0, "latency_ms_mean": 6731.9, "usd_sum": 0.00144 } }, { "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": 307, "output_tokens": 2, "latency_ms": 4656.6, "usd": 0.000404, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 307, "output_tokens": 2, "latency_ms": 5107.4, "usd": 0.000404, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 307, "output_tokens": 2, "latency_ms": 3707.8, "usd": 0.000404, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 307.0, "output_tokens_mean": 2.0, "latency_ms_mean": 4490.6, "usd_sum": 0.001212 } }, { "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": 416, "output_tokens": 1, "latency_ms": 3951.0, "usd": 0.00053, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 416, "output_tokens": 1, "latency_ms": 3746.3, "usd": 0.00053, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 416, "output_tokens": 1, "latency_ms": 3940.7, "usd": 0.00053, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 416.0, "output_tokens_mean": 1.0, "latency_ms_mean": 3879.333, "usd_sum": 0.00159 } }, { "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": 339, "output_tokens": 1, "latency_ms": 10211.4, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 1, "latency_ms": 7267.7, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 1, "latency_ms": 6248.9, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 339.0, "output_tokens_mean": 1.0, "latency_ms_mean": 7909.333, "usd_sum": 0.001302 } }, { "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": 339, "output_tokens": 1, "latency_ms": 7373.1, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 1, "latency_ms": 8454.5, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 339, "output_tokens": 1, "latency_ms": 12384.8, "usd": 0.000434, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 339.0, "output_tokens_mean": 1.0, "latency_ms_mean": 9404.133, "usd_sum": 0.001302 } }, { "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": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 411, "output_tokens": 1, "latency_ms": 14305.6, "usd": 0.000524, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 411, "output_tokens": 1, "latency_ms": 14021.0, "usd": 0.000524, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 411, "output_tokens": 1, "latency_ms": 10222.3, "usd": 0.000524, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 411.0, "output_tokens_mean": 1.0, "latency_ms_mean": 12849.633, "usd_sum": 0.001572 } }, { "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": 409, "output_tokens": 2, "latency_ms": 6450.9, "usd": 0.000531, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 409, "output_tokens": 2, "latency_ms": 9450.4, "usd": 0.000531, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 409, "output_tokens": 2, "latency_ms": 17684.5, "usd": 0.000531, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 409.0, "output_tokens_mean": 2.0, "latency_ms_mean": 11195.267, "usd_sum": 0.001593 } }, { "task_id": "ogs:core:benchmark-task:vocab-013", "category": "vocabulary", "capability": "component_role_vocabulary", "difficulty": "medium", "cuisine_region": "moroccan", "scorer": "exact_match", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "dc3e62daf8bdf21a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nReturn the single OGS component role that best fits harissa stirred into a lamb tagine at service.\n\nINPUT:\n{\n \"description\": \"a spoonful of fiery harissa stirred into a lamb-and-apricot tagine at service\"\n}\n\nANSWER FORMAT: one_of:main_protein,main_vegetable,starch,sauce,fat_component,acid_component,aromatic_garnish,seasoning,textural_element", "expected": { "value": "seasoning" }, "samples": [ { "sample": 0, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 364, "output_tokens": 2, "latency_ms": 10881.8, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 364, "output_tokens": 2, "latency_ms": 8047.1, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 364, "output_tokens": 2, "latency_ms": 8308.3, "usd": 0.000475, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 2.0, "latency_ms_mean": 9079.067, "usd_sum": 0.001425 } }, { "task_id": "ogs:core:benchmark-task:vocab-014", "category": "vocabulary", "capability": "qualifier_vocabulary", "difficulty": "medium", "cuisine_region": "chinese", "scorer": "exact_match", "context_needs": [ "vocab.qualifiers" ], "prompt_template_hash": "3980456a47e9b7c6", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nSelect the OGS aromatic qualifier that best describes the state of Sichuan peppercorn as it is commonly used — whole, toasted, and ground over finished mapo tofu.\n\nINPUT:\n{\n \"item\": \"Sichuan peppercorn (Zanthoxylum), whole, pan-toasted just before grinding over the dish\"\n}\n\nANSWER FORMAT: one_of:fresh,dried,cooked,candied,fermented,zest,overripe", "expected": { "value": "dried" }, "samples": [ { "sample": 0, "raw_response": "cooked", "compliant": true, "score": 0.0, "detail": { "predicted": "cooked", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 6552.6, "usd": 0.000444, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "cooked", "compliant": true, "score": 0.0, "detail": { "predicted": "cooked", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 5597.2, "usd": 0.000444, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "cooked", "compliant": true, "score": 0.0, "detail": { "predicted": "cooked", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 347, "output_tokens": 1, "latency_ms": 5870.8, "usd": 0.000444, "model_version": "gemini-2.5-pro", "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": 347.0, "output_tokens_mean": 1.0, "latency_ms_mean": 6006.867, "usd_sum": 0.001332 } }, { "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": 402, "output_tokens": 2, "latency_ms": 3881.8, "usd": 0.000523, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 2, "latency_ms": 3827.9, "usd": 0.000523, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 2, "latency_ms": 3450.8, "usd": 0.000523, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 402.0, "output_tokens_mean": 2.0, "latency_ms_mean": 3720.167, "usd_sum": 0.001569 } }, { "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": 326, "output_tokens": 1, "latency_ms": 7880.6, "usd": 0.000418, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 326, "output_tokens": 1, "latency_ms": 8544.7, "usd": 0.000418, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 326, "output_tokens": 1, "latency_ms": 7169.4, "usd": 0.000418, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 1.0, "latency_ms_mean": 7864.9, "usd_sum": 0.001254 } }, { "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": 327, "output_tokens": 2, "latency_ms": 8860.1, "usd": 0.000429, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 327, "output_tokens": 2, "latency_ms": 6667.3, "usd": 0.000429, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 327, "output_tokens": 2, "latency_ms": 7463.2, "usd": 0.000429, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 327.0, "output_tokens_mean": 2.0, "latency_ms_mean": 7663.533, "usd_sum": 0.001287 } }, { "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": 357, "output_tokens": 3, "latency_ms": 8068.6, "usd": 0.000476, "model_version": "gemini-2.5-pro", "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": 357, "output_tokens": 3, "latency_ms": 8440.5, "usd": 0.000476, "model_version": "gemini-2.5-pro", "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": 357, "output_tokens": 3, "latency_ms": 10319.6, "usd": 0.000476, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 357.0, "output_tokens_mean": 3.0, "latency_ms_mean": 8942.9, "usd_sum": 0.001428 } }, { "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": 410, "output_tokens": 2, "latency_ms": 6961.4, "usd": 0.000533, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 410, "output_tokens": 2, "latency_ms": 8478.5, "usd": 0.000533, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 410, "output_tokens": 2, "latency_ms": 6470.8, "usd": 0.000533, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 410.0, "output_tokens_mean": 2.0, "latency_ms_mean": 7303.567, "usd_sum": 0.001599 } }, { "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": 402, "output_tokens": 1, "latency_ms": 6039.7, "usd": 0.000513, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 1, "latency_ms": 3801.1, "usd": 0.000513, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 402, "output_tokens": 1, "latency_ms": 4923.2, "usd": 0.000513, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 402.0, "output_tokens_mean": 1.0, "latency_ms_mean": 4921.333, "usd_sum": 0.001539 } }, { "task_id": "ogs:core:benchmark-task:xplain-001", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "a75ad0ee2a385794", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nFrom the OGS explanation-code vocabulary, return the set of codes that best explain WHY the pairing below is excellent. Respond as a JSON array of code IDs. Pick 3 to 6 most relevant positive codes.\n\nINPUT:\n{\n \"dish\": \"A5 wagyu with black truffle jus (very rich, high umami, earthy aromatics, full body)\",\n \"beverage\": \"Barolo 2018 (Nebbiolo, high tannin, high acidity, full body, tar/forest-floor)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_FAT", "STRUCT_INTENSITY_MATCH", "AROMA_SHARED_EARTH", "STRUCT_BODY_ALIGN", "HARMONY_FLAVOR_CONVERGE" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"STRUCT_TANNIN_FAT\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_BODY_ALIGN\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.7273, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "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": 1231, "output_tokens": 65, "latency_ms": 11547.9, "usd": 0.002189, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_BODY_ALIGN\",\n \"STRUCT_UMAMI_ENHANCE\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.5455, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "precision": 0.5, "recall": 0.6 }, "metrics": { "input_tokens": 1231, "output_tokens": 67, "latency_ms": 12082.7, "usd": 0.002209, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_BODY_ALIGN\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "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": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1231, "output_tokens": 55, "latency_ms": 15881.1, "usd": 0.002089, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.6243, "score_summary": { "mean": 0.6243, "stdev": 0.0933, "sem": 0.0539, "ci95_lo": 0.5187, "ci95_hi": 0.7298, "n": 3 }, "score_if_valid": 0.6243, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1231.0, "output_tokens_mean": 62.333, "latency_ms_mean": 13170.567, "usd_sum": 0.006487 } }, { "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": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_UMAMI_ENHANCE\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.5, "recall": 0.4 }, "metrics": { "input_tokens": 1194, "output_tokens": 47, "latency_ms": 12357.3, "usd": 0.001962, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_MINERAL\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1194, "output_tokens": 54, "latency_ms": 12307.7, "usd": 0.002033, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"REFRESH_ACID\"\n]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1194, "output_tokens": 54, "latency_ms": 17582.6, "usd": 0.002033, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.5481, "score_summary": { "mean": 0.5481, "stdev": 0.0898, "sem": 0.0519, "ci95_lo": 0.4465, "ci95_hi": 0.6498, "n": 3 }, "score_if_valid": 0.5481, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1194.0, "output_tokens_mean": 51.667, "latency_ms_mean": 14082.533, "usd_sum": 0.006028 } }, { "task_id": "ogs:core:benchmark-task:xplain-003", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "3440bcf3978a1c58", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (2 to 4 codes).\n\nINPUT:\n{\n \"dish\": \"crispy buttermilk fried chicken\",\n \"beverage\": \"non-vintage Brut Champagne\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "REFRESH_EFFERVESCE", "REFRESH_ACID", "CONTRAST_RICH_CRISP" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"REFRESH_EFFERVESCE\",\n \"REFRESH_ACID\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.75, "recall": 1.0 }, "metrics": { "input_tokens": 1179, "output_tokens": 45, "latency_ms": 16001.4, "usd": 0.001924, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"REFRESH_EFFERVESCE\",\n \"REFRESH_ACID\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_ACIDITY_BALANCE\"\n]", "compliant": true, "score": 0.8571, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.75, "recall": 1.0 }, "metrics": { "input_tokens": 1179, "output_tokens": 46, "latency_ms": 17072.6, "usd": 0.001934, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"REFRESH_EFFERVESCE\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 0.6667, "recall": 0.6667 }, "metrics": { "input_tokens": 1179, "output_tokens": 37, "latency_ms": 22249.5, "usd": 0.001844, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.7936, "score_summary": { "mean": 0.7936, "stdev": 0.1099, "sem": 0.0635, "ci95_lo": 0.6692, "ci95_hi": 0.918, "n": 3 }, "score_if_valid": 0.7936, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1179.0, "output_tokens_mean": 42.667, "latency_ms_mean": 18441.167, "usd_sum": 0.005702 } }, { "task_id": "ogs:core:benchmark-task:xplain-004", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "b3249dafda966f70", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain the success of the pairing below. Respond as a JSON array (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"seared foie gras on brioche (very rich, fatty, slightly sweet-savoury)\",\n \"beverage\": \"Sauternes (botrytised sweet white, high residual sugar, high acidity)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "STRUCT_ACIDITY_BALANCE", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\",\n \"CONTRAST_SWEET_SALTY\",\n \"HARMONY_REGIONAL\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1202, "output_tokens": 59, "latency_ms": 21296.9, "usd": 0.002092, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_SWEET_OFFSET\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1202, "output_tokens": 56, "latency_ms": 18124.2, "usd": 0.002063, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"HARMONY_REGIONAL\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_BODY_ALIGN\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1202, "output_tokens": 43, "latency_ms": 14932.1, "usd": 0.001932, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.6852, "score_summary": { "mean": 0.6852, "stdev": 0.1951, "sem": 0.1126, "ci95_lo": 0.4644, "ci95_hi": 0.906, "n": 3 }, "score_if_valid": 0.6852, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1202.0, "output_tokens_mean": 52.667, "latency_ms_mean": 18117.733, "usd_sum": 0.006087 } }, { "task_id": "ogs:core:benchmark-task:xplain-005", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "0cb2f1946943a0e2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain why the pairing works. Respond as a JSON array (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"charcoal-grilled lamb rack with rosemary, black pepper crust, charred edges\",\n \"beverage\": \"Northern Rhone Syrah (Cote-Rotie) — black pepper, violet, smoked meat, moderate-high tannin\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "AROMA_SHARED_HERBAL", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"STRUCT_TANNIN_FAT\",\n \"AROMA_SHARED_SPICE\",\n \"AROMA_SHARED_WOOD\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.75, "recall": 0.6 }, "metrics": { "input_tokens": 1205, "output_tokens": 45, "latency_ms": 11086.6, "usd": 0.001956, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"AROMA_SHARED_SPICE\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"AROMA_SHARED_WOOD\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.75, "recall": 0.6 }, "metrics": { "input_tokens": 1205, "output_tokens": 46, "latency_ms": 14116.1, "usd": 0.001966, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"AROMA_SHARED_SPICE\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"AROMA_SHARED_HERBAL\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "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": 1205, "output_tokens": 62, "latency_ms": 15157.1, "usd": 0.002126, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.6445, "score_summary": { "mean": 0.6445, "stdev": 0.0385, "sem": 0.0222, "ci95_lo": 0.6009, "ci95_hi": 0.688, "n": 3 }, "score_if_valid": 0.6445, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1205.0, "output_tokens_mean": 51.0, "latency_ms_mean": 13453.267, "usd_sum": 0.006048 } }, { "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": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_UMAMI_ENHANCE\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1192, "output_tokens": 47, "latency_ms": 13412.7, "usd": 0.00196, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"STRUCT_TANNIN_FAT\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1192, "output_tokens": 50, "latency_ms": 14535.5, "usd": 0.00199, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_ACID\",\n \"STRUCT_UMAMI_ENHANCE\",\n \"STRUCT_TANNIN_FAT\"\n]\n```", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1192, "output_tokens": 61, "latency_ms": 13315.6, "usd": 0.0021, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.4815, "score_summary": { "mean": 0.4815, "stdev": 0.0321, "sem": 0.0185, "ci95_lo": 0.4451, "ci95_hi": 0.5178, "n": 3 }, "score_if_valid": 0.4815, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1192.0, "output_tokens_mean": 52.667, "latency_ms_mean": 13754.6, "usd_sum": 0.00605 } }, { "task_id": "ogs:core:benchmark-task:xplain-007", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "chinese", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "497adc64f3303eb4", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"mapo tofu with Sichuan peppercorn\",\n \"beverage\": \"off-dry German Spätlese Riesling\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "CONTRAST_SWEET_SALTY" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1188, "output_tokens": 45, "latency_ms": 12802.5, "usd": 0.001935, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n[\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"STRUCT_INTENSITY_MATCH\",\n \"CONTRAST_SWEET_SALTY\"\n]\n```", "compliant": true, "score": 1.0, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1188, "output_tokens": 50, "latency_ms": 16939.3, "usd": 0.001985, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_SWEET_OFFSET\",\n \"REFRESH_ACID\",\n \"STRUCT_INTENSITY_MATCH\",\n \"CONTRAST_RICH_CRISP\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1188, "output_tokens": 44, "latency_ms": 12639.7, "usd": 0.001925, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.9167, "score_summary": { "mean": 0.9167, "stdev": 0.1443, "sem": 0.0833, "ci95_lo": 0.7533, "ci95_hi": 1.08, "n": 3 }, "score_if_valid": 0.9167, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1188.0, "output_tokens_mean": 46.333, "latency_ms_mean": 14127.167, "usd_sum": 0.005845 } }, { "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": "[\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_TANNIN_FAT\",\n \"AROMA_SHARED_HERBAL\",\n \"AROMA_SHARED_SPICE\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1185, "output_tokens": 58, "latency_ms": 12393.7, "usd": 0.002061, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"STRUCT_TANNIN_FAT\",\n \"AROMA_SHARED_HERBAL\",\n \"STRUCT_INTENSITY_MATCH\",\n \"AROMA_SHARED_SPICE\",\n \"STRUCT_ACIDITY_BALANCE\"\n]", "compliant": true, "score": 0.2222, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "AROMA_SHARED_SPICE", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.2, "recall": 0.25 }, "metrics": { "input_tokens": 1185, "output_tokens": 57, "latency_ms": 16544.5, "usd": 0.002051, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_TANNIN_FAT\",\n \"AROMA_SHARED_HERBAL\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"STRUCT_BODY_ALIGN\"\n]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 1185, "output_tokens": 61, "latency_ms": 12230.0, "usd": 0.002091, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.5185, "score_summary": { "mean": 0.5185, "stdev": 0.3395, "sem": 0.196, "ci95_lo": 0.1344, "ci95_hi": 0.9026, "n": 3 }, "score_if_valid": 0.5185, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1185.0, "output_tokens_mean": 58.667, "latency_ms_mean": 13722.733, "usd_sum": 0.006203 } }, { "task_id": "ogs:core:benchmark-task:xplain-009", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "thai", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "c077c498ceed5f73", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"Thai green curry with chicken and Thai basil\",\n \"beverage\": \"off-dry New Zealand Sauvignon Blanc\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"STRUCT_SWEET_OFFSET\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_HERBAL\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1185, "output_tokens": 45, "latency_ms": 14693.4, "usd": 0.001931, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"STRUCT_SWEET_OFFSET\",\n \"AROMA_SHARED_HERBAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1185, "output_tokens": 45, "latency_ms": 14612.8, "usd": 0.001931, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_SWEET_OFFSET\",\n \"AROMA_SHARED_HERBAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1185, "output_tokens": 45, "latency_ms": 11035.5, "usd": 0.001931, "model_version": "gemini-2.5-pro", "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": 1185.0, "output_tokens_mean": 45.0, "latency_ms_mean": 13447.233, "usd_sum": 0.005793 } }, { "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": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_MINERAL\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.75, "recall": 0.6 }, "metrics": { "input_tokens": 1180, "output_tokens": 43, "latency_ms": 17815.6, "usd": 0.001905, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"CONTRAST_RICH_CRISP\"\n]\n```", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.5, "recall": 0.4 }, "metrics": { "input_tokens": 1180, "output_tokens": 52, "latency_ms": 18301.0, "usd": 0.001995, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.5, "recall": 0.4 }, "metrics": { "input_tokens": 1180, "output_tokens": 45, "latency_ms": 14263.5, "usd": 0.001925, "model_version": "gemini-2.5-pro", "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": 1180.0, "output_tokens_mean": 46.667, "latency_ms_mean": 16793.367, "usd_sum": 0.005825 } }, { "task_id": "ogs:core:benchmark-task:xplain-011", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "mexican", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "1dfeb782059a4814", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"tacos al pastor with pineapple and chili\",\n \"beverage\": \"dry sparkling rosé (Cava rosado)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "REFRESH_EFFERVESCE", "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"REFRESH_EFFERVESCE\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\",\n \"CONTRAST_SWEET_ACID\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_ACID", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1186, "output_tokens": 50, "latency_ms": 17222.6, "usd": 0.001982, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"REFRESH_EFFERVESCE\",\n \"CONTRAST_RICH_CRISP\",\n \"CONTRAST_SWEET_ACID\",\n \"AROMA_SHARED_FRUIT\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_ACID", "REFRESH_EFFERVESCE" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1186, "output_tokens": 50, "latency_ms": 16065.0, "usd": 0.001982, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n[\n \"REFRESH_EFFERVESCE\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_SWEET_ACID\",\n \"AROMA_SHARED_FRUIT\"\n]\n```", "compliant": true, "score": 0.5, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_ACID", "REFRESH_EFFERVESCE", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1186, "output_tokens": 54, "latency_ms": 22062.9, "usd": 0.002022, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.5833, "score_summary": { "mean": 0.5833, "stdev": 0.1443, "sem": 0.0833, "ci95_lo": 0.42, "ci95_hi": 0.7467, "n": 3 }, "score_if_valid": 0.5833, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1186.0, "output_tokens_mean": 51.333, "latency_ms_mean": 18450.167, "usd_sum": 0.005986 } }, { "task_id": "ogs:core:benchmark-task:xplain-012", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "28df36c8ae155697", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"duck confit, crispy skin\",\n \"beverage\": \"mature Burgundy Pinot Noir (10 years)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_FAT", "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "HARMONY_COMPLEXITY_MATCH" ] }, "samples": [ { "sample": 0, "raw_response": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_TANNIN_FAT\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1184, "output_tokens": 46, "latency_ms": 11816.7, "usd": 0.00194, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_UMAMI_ENHANCE\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_FAT", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1184, "output_tokens": 58, "latency_ms": 18227.7, "usd": 0.00206, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"AROMA_SHARED_EARTH\",\n \"STRUCT_TANNIN_PROTEIN\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1184, "output_tokens": 47, "latency_ms": 9731.6, "usd": 0.00195, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.6389, "score_summary": { "mean": 0.6389, "stdev": 0.1273, "sem": 0.0735, "ci95_lo": 0.4948, "ci95_hi": 0.783, "n": 3 }, "score_if_valid": 0.6389, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1184.0, "output_tokens_mean": 50.333, "latency_ms_mean": 13258.667, "usd_sum": 0.00595 } }, { "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": "```json\n[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"CONTRAST_RICH_CRISP\"\n]\n```", "compliant": true, "score": 0.25, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.25, "recall": 0.25 }, "metrics": { "input_tokens": 1189, "output_tokens": 56, "latency_ms": 17281.3, "usd": 0.002046, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"REFRESH_ACID\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"CONTRAST_RICH_CRISP\"\n]", "compliant": true, "score": 0.25, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "REFRESH_ACID" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.25, "recall": 0.25 }, "metrics": { "input_tokens": 1189, "output_tokens": 49, "latency_ms": 13115.5, "usd": 0.001976, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"REFRESH_ACID\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"STRUCT_UMAMI_ENHANCE\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1189, "output_tokens": 49, "latency_ms": 13731.8, "usd": 0.001976, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.3333, "score_summary": { "mean": 0.3333, "stdev": 0.1443, "sem": 0.0833, "ci95_lo": 0.17, "ci95_hi": 0.4967, "n": 3 }, "score_if_valid": 0.3333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1189.0, "output_tokens_mean": 51.333, "latency_ms_mean": 14709.533, "usd_sum": 0.005998 } }, { "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": "[\n \"STRUCT_UMAMI_ENHANCE\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_INTENSITY_MATCH\",\n \"AROMA_SHARED_FRUIT\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1189, "output_tokens": 48, "latency_ms": 15255.8, "usd": 0.001966, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n[\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_UMAMI_ENHANCE\",\n \"AROMA_SHARED_FRUIT\",\n \"STRUCT_BODY_ALIGN\"\n]\n```", "compliant": true, "score": 0.75, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 1189, "output_tokens": 52, "latency_ms": 14437.5, "usd": 0.002006, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_UMAMI_ENHANCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.25, "detail": { "predicted": [ "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.25, "recall": 0.25 }, "metrics": { "input_tokens": 1189, "output_tokens": 52, "latency_ms": 9010.9, "usd": 0.002006, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.5, "score_summary": { "mean": 0.5, "stdev": 0.25, "sem": 0.1443, "ci95_lo": 0.2171, "ci95_hi": 0.7829, "n": 3 }, "score_if_valid": 0.5, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1189.0, "output_tokens_mean": 50.667, "latency_ms_mean": 12901.4, "usd_sum": 0.005978 } }, { "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": "[\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_COMPLEXITY_MATCH\",\n \"STRUCT_BODY_ALIGN\",\n \"STRUCT_TANNIN_FAT\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "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": 1177, "output_tokens": 59, "latency_ms": 16773.1, "usd": 0.002061, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_INTENSITY_MATCH\",\n \"HARMONY_COMPLEXITY_MATCH\",\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_BODY_ALIGN\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "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": 1177, "output_tokens": 59, "latency_ms": 12143.0, "usd": 0.002061, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"CONTRAST_SWEET_SALTY\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_BODY_ALIGN\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"STRUCT_TANNIN_FAT\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "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": 1177, "output_tokens": 61, "latency_ms": 12869.8, "usd": 0.002081, "model_version": "gemini-2.5-pro", "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": 1177.0, "output_tokens_mean": 59.667, "latency_ms_mean": 13928.633, "usd_sum": 0.006203 } }, { "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": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_UMAMI_ENHANCE\",\n \"STRUCT_ACIDITY_BALANCE\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.75, "recall": 0.6 }, "metrics": { "input_tokens": 1184, "output_tokens": 46, "latency_ms": 16988.3, "usd": 0.00194, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n[\n \"HARMONY_REGIONAL\",\n \"STRUCT_INTENSITY_MATCH\",\n \"REFRESH_ACID\",\n \"STRUCT_UMAMI_ENHANCE\",\n \"CONTRAST_RICH_CRISP\"\n]\n```", "compliant": true, "score": 0.6, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 1184, "output_tokens": 61, "latency_ms": 19453.1, "usd": 0.00209, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n[\n \"HARMONY_REGIONAL\",\n \"STRUCT_INTENSITY_MATCH\",\n \"REFRESH_ACID\",\n \"STRUCT_UMAMI_ENHANCE\"\n]\n```", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.75, "recall": 0.6 }, "metrics": { "input_tokens": 1184, "output_tokens": 49, "latency_ms": 22937.2, "usd": 0.00197, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.6445, "score_summary": { "mean": 0.6445, "stdev": 0.0385, "sem": 0.0222, "ci95_lo": 0.6009, "ci95_hi": 0.688, "n": 3 }, "score_if_valid": 0.6445, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1184.0, "output_tokens_mean": 52.0, "latency_ms_mean": 19792.867, "usd_sum": 0.006 } }, { "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": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_MINERAL\",\n \"STRUCT_INTENSITY_MATCH\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1187, "output_tokens": 43, "latency_ms": 11602.2, "usd": 0.001914, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "```json\n[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"REFRESH_ACID\",\n \"STRUCT_INTENSITY_MATCH\",\n \"REFRESH_MINERAL\"\n]\n```", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1187, "output_tokens": 57, "latency_ms": 14916.5, "usd": 0.002054, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_INTENSITY_MATCH\",\n \"REFRESH_MINERAL\"\n]", "compliant": true, "score": 0.5, "detail": { "predicted": [ "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.5, "recall": 0.5 }, "metrics": { "input_tokens": 1187, "output_tokens": 43, "latency_ms": 14733.5, "usd": 0.001914, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.5556, "score_summary": { "mean": 0.5556, "stdev": 0.0962, "sem": 0.0556, "ci95_lo": 0.4467, "ci95_hi": 0.6645, "n": 3 }, "score_if_valid": 0.5556, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1187.0, "output_tokens_mean": 47.667, "latency_ms_mean": 13750.733, "usd_sum": 0.005882 } }, { "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": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_SWEET_SALTY\",\n \"CONTRAST_RICH_CRISP\",\n \"HARMONY_COMPLEXITY_MATCH\"\n]", "compliant": true, "score": 0.25, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.25, "recall": 0.25 }, "metrics": { "input_tokens": 1194, "output_tokens": 52, "latency_ms": 17833.4, "usd": 0.002012, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\",\n \"CONTRAST_SWEET_SALTY\",\n \"HARMONY_COMPLEXITY_MATCH\"\n]", "compliant": true, "score": 0.25, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.25, "recall": 0.25 }, "metrics": { "input_tokens": 1194, "output_tokens": 52, "latency_ms": 16785.9, "usd": 0.002012, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n[\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_SWEET_OFFSET\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]\n```", "compliant": true, "score": 0.25, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_FLAVOR_CONVERGE", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.25, "recall": 0.25 }, "metrics": { "input_tokens": 1194, "output_tokens": 56, "latency_ms": 19766.4, "usd": 0.002052, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } } ], "score": 0.25, "score_summary": { "mean": 0.25, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.25, "ci95_hi": 0.25, "n": 3 }, "score_if_valid": 0.25, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1194.0, "output_tokens_mean": 53.333, "latency_ms_mean": 18128.567, "usd_sum": 0.006076 } }, { "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": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_BODY_ALIGN\",\n \"AROMA_SHARED_EARTH\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1192, "output_tokens": 55, "latency_ms": 12772.8, "usd": 0.00204, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"HARMONY_REGIONAL\",\n \"STRUCT_TANNIN_FAT\",\n \"STRUCT_INTENSITY_MATCH\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_TANNIN_PROTEIN\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1192, "output_tokens": 57, "latency_ms": 12312.3, "usd": 0.00206, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "```json\n[\n \"HARMONY_REGIONAL\",\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_TANNIN_PROTEIN\",\n \"STRUCT_BODY_ALIGN\",\n \"STRUCT_INTENSITY_MATCH\"\n]\n```", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1192, "output_tokens": 60, "latency_ms": 16516.4, "usd": 0.00209, "model_version": "gemini-2.5-pro", "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": 1192.0, "output_tokens_mean": 57.333, "latency_ms_mean": 13867.167, "usd_sum": 0.00619 } }, { "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": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_SWEET_OFFSET\",\n \"HARMONY_REGIONAL\",\n \"STRUCT_BODY_ALIGN\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1181, "output_tokens": 55, "latency_ms": 12870.6, "usd": 0.002026, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 1, "raw_response": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"CONTRAST_RICH_CRISP\",\n \"STRUCT_BODY_ALIGN\",\n \"HARMONY_REGIONAL\",\n \"HARMONY_FLAVOR_CONVERGE\"\n]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 1181, "output_tokens": 60, "latency_ms": 16078.7, "usd": 0.002076, "model_version": "gemini-2.5-pro", "finish_reason": "STOP" } }, { "sample": 2, "raw_response": "[\n \"STRUCT_ACIDITY_BALANCE\",\n \"STRUCT_SWEET_OFFSET\",\n \"STRUCT_BODY_ALIGN\",\n \"HARMONY_FLAVOR_CONVERGE\",\n \"HARMONY_REGIONAL\"\n]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_FLAVOR_CONVERGE", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 1181, "output_tokens": 58, "latency_ms": 16086.8, "usd": 0.002056, "model_version": "gemini-2.5-pro", "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": 1181.0, "output_tokens_mean": 57.667, "latency_ms_mean": 15012.033, "usd_sum": 0.006158 } } ], "category_scores": { "composition": { "mean_score": 0.9107, "ci95_lo": 0.8071, "ci95_hi": 1.0142, "stdev": 0.2364, "task_count": 20, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.9107 }, "dietary": { "mean_score": 0.8125, "ci95_lo": 0.594, "ci95_hi": 1.031, "stdev": 0.3862, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.8125 }, "explanation": { "mean_score": 0.5845, "ci95_lo": 0.52, "ci95_hi": 0.649, "stdev": 0.1472, "task_count": 20, "weight": 0.1, "format_rate": 1.0, "score_if_valid": 0.5845 }, "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": 0.8551, "ci95_lo": 0.7121, "ci95_hi": 0.9981, "stdev": 0.2308, "task_count": 10, "weight": 0.03, "format_rate": 1.0, "score_if_valid": 0.8551 }, "pairing": { "mean_score": 1.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "stdev": 0.0, "task_count": 22, "weight": 0.15, "format_rate": 1.0, "score_if_valid": 1.0 }, "regional": { "mean_score": 0.9722, "ci95_lo": 0.9178, "ci95_hi": 1.0267, "stdev": 0.1361, "task_count": 24, "weight": 0.05, "format_rate": 1.0, "score_if_valid": 0.9722 }, "risk": { "mean_score": 0.8333, "ci95_lo": 0.6726, "ci95_hi": 0.9941, "stdev": 0.3667, "task_count": 20, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 0.8333 }, "safety": { "mean_score": 0.9317, "ci95_lo": 0.8223, "ci95_hi": 1.0412, "stdev": 0.1935, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.9317 }, "sensory": { "mean_score": 0.5341, "ci95_lo": 0.4059, "ci95_hi": 0.6624, "stdev": 0.2999, "task_count": 21, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.5341 }, "structured_output": { "mean_score": 0.975, "ci95_lo": 0.9393, "ci95_hi": 1.0107, "stdev": 0.0816, "task_count": 20, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.975 }, "vocabulary": { "mean_score": 0.942, "ci95_lo": 0.8534, "ci95_hi": 1.0306, "stdev": 0.2168, "task_count": 23, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 0.942 } }, "aggregate": { "score": 84.98, "ci95_lo": 81.96, "ci95_hi": 87.99, "scale": "0-100", "partial": false, "missing_categories": [] }, "metrics": { "latency_ms_mean": 9527.49, "latency_ms_median": 8765.233, "input_tokens_mean": 792.2, "output_tokens_mean": 61.6, "usd_total": 1.026691, "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)." } }