{ "benchmark_version": "0.3.0", "ogs_version": "0.2.0", "run_id": "cd699e21-25bc-4c02-a40e-21a7ec4cf7f7", "run_at": "2026-04-18T06:42:42.856875+00:00", "model": { "id": "claude-opus-4-7", "adapter": "anthropic", "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": 633, "output_tokens": 6, "latency_ms": 1212.3, "usd": 0.009945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "3", "compliant": true, "score": 1.0, "detail": { "predicted": 3.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 633, "output_tokens": 6, "latency_ms": 940.2, "usd": 0.009945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "3", "compliant": true, "score": 1.0, "detail": { "predicted": 3.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 633, "output_tokens": 6, "latency_ms": 1197.8, "usd": 0.009945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 633.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1116.767, "usd_sum": 0.029835 } }, { "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": 619, "output_tokens": 6, "latency_ms": 1465.0, "usd": 0.009735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 619, "output_tokens": 6, "latency_ms": 1175.6, "usd": 0.009735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 619, "output_tokens": 6, "latency_ms": 1337.7, "usd": 0.009735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 619.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1326.1, "usd_sum": 0.029205 } }, { "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": 633, "output_tokens": 6, "latency_ms": 1010.3, "usd": 0.009945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 633, "output_tokens": 6, "latency_ms": 1043.9, "usd": 0.009945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 633, "output_tokens": 6, "latency_ms": 1105.6, "usd": 0.009945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 633.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1053.267, "usd_sum": 0.029835 } }, { "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": 670, "output_tokens": 6, "latency_ms": 918.7, "usd": 0.0105, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 670, "output_tokens": 6, "latency_ms": 1355.0, "usd": 0.0105, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 670, "output_tokens": 6, "latency_ms": 1223.9, "usd": 0.0105, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 670.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1165.867, "usd_sum": 0.0315 } }, { "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": 562, "output_tokens": 8, "latency_ms": 2122.8, "usd": 0.00903, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "textural_element", "compliant": true, "score": 1.0, "detail": { "predicted": "textural_element", "expected": "textural_element", "aliases": [] }, "metrics": { "input_tokens": 562, "output_tokens": 8, "latency_ms": 1118.9, "usd": 0.00903, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "textural_element", "compliant": true, "score": 1.0, "detail": { "predicted": "textural_element", "expected": "textural_element", "aliases": [] }, "metrics": { "input_tokens": 562, "output_tokens": 8, "latency_ms": 811.2, "usd": 0.00903, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 562.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1350.967, "usd_sum": 0.02709 } }, { "task_id": "ogs:core:benchmark-task:comp-006", "category": "composition", "capability": "component_set_identification", "difficulty": "hard", "cuisine_region": "italian", "scorer": "set_f1", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "bb37bf992b2f6c39", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nList the OGS component ROLES that appear in a classic Roman spaghetti alla carbonara (guanciale, eggs, pecorino romano, spaghetti, black pepper). Respond with a JSON array of role strings from the OGS vocabulary, without duplicates, in any order.\n\nINPUT:\n{\n \"dish\": \"classic Roman spaghetti alla carbonara\",\n \"components_present\": [\n \"spaghetti\",\n \"guanciale\",\n \"egg yolks\",\n \"pecorino romano\",\n \"black pepper\"\n ]\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\",\n \"enum\": [\n \"main_protein\",\n \"main_vegetable\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n ]\n },\n \"uniqueItems\": true\n}", "expected": { "values": [ "starch", "main_protein", "fat_component", "sauce", "seasoning" ] }, "samples": [ { "sample": 0, "raw_response": "[\"starch\",\"main_protein\",\"fat_component\",\"sauce\",\"seasoning\"]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 749, "output_tokens": 29, "latency_ms": 4233.7, "usd": 0.01341, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"starch\",\"main_protein\",\"fat_component\",\"sauce\",\"seasoning\"]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 749, "output_tokens": 29, "latency_ms": 1445.6, "usd": 0.01341, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"starch\",\"main_protein\",\"fat_component\",\"sauce\",\"seasoning\"]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "expected": [ "fat_component", "main_protein", "sauce", "seasoning", "starch" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 749, "output_tokens": 29, "latency_ms": 1364.1, "usd": 0.01341, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 749.0, "output_tokens_mean": 29.0, "latency_ms_mean": 2347.8, "usd_sum": 0.04023 } }, { "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": 496, "output_tokens": 6, "latency_ms": 1221.3, "usd": 0.00789, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 496, "output_tokens": 6, "latency_ms": 1145.1, "usd": 0.00789, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 496, "output_tokens": 6, "latency_ms": 1118.6, "usd": 0.00789, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 496.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1161.667, "usd_sum": 0.02367 } }, { "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": 627, "output_tokens": 6, "latency_ms": 1123.6, "usd": 0.009855, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 627, "output_tokens": 6, "latency_ms": 984.6, "usd": 0.009855, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 627, "output_tokens": 6, "latency_ms": 1038.0, "usd": 0.009855, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 627.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1048.733, "usd_sum": 0.029565 } }, { "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": 614, "output_tokens": 6, "latency_ms": 1200.4, "usd": 0.00966, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 614, "output_tokens": 6, "latency_ms": 1180.8, "usd": 0.00966, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "0", "compliant": true, "score": 1.0, "detail": { "predicted": 0.0, "expected": 0.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 614, "output_tokens": 6, "latency_ms": 1010.9, "usd": 0.00966, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 614.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1130.7, "usd_sum": 0.02898 } }, { "task_id": "ogs:core:benchmark-task:comp-010", "category": "composition", "capability": "maillard_index", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_mae", "context_needs": [ "scales.maillard_index" ], "prompt_template_hash": "d420afcaea603a0e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Maillard index (0-5 integer)\n\n- 0: no browning (raw, poached, steamed)\n- 1: pale gold (soft-baked dough, lightly sauteed)\n- 2: golden brown (roasted chicken skin)\n- 3: deep mahogany (well-seared steak crust, duck breast skin)\n- 4: very dark brown with bitter edge (heavy crust, blackened fish)\n- 5: fully charred (intentionally blackened, carbonised)\n\n---\n\nUsing the OGS Maillard index, return the integer for a scallop seared in hot butter until a deep golden crust forms on one side.\n\nINPUT:\n{\n \"description\": \"diver scallop seared in foaming butter, one side deep golden, interior translucent\"\n}\n\nANSWER FORMAT: integer_0_5", "expected": { "value": 3, "tolerance": 1 }, "samples": [ { "sample": 0, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 618, "output_tokens": 6, "latency_ms": 3388.9, "usd": 0.00972, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 618, "output_tokens": 6, "latency_ms": 1048.5, "usd": 0.00972, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 618, "output_tokens": 6, "latency_ms": 1121.3, "usd": 0.00972, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 618.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1852.9, "usd_sum": 0.02916 } }, { "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": 610, "output_tokens": 6, "latency_ms": 1126.6, "usd": 0.0096, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 610, "output_tokens": 6, "latency_ms": 1109.7, "usd": 0.0096, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 0.0, "detail": { "predicted": 2.0, "expected": 3.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 610, "output_tokens": 6, "latency_ms": 1003.2, "usd": 0.0096, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 610.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1079.833, "usd_sum": 0.0288 } }, { "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": 607, "output_tokens": 6, "latency_ms": 1225.2, "usd": 0.009555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "5", "compliant": true, "score": 1.0, "detail": { "predicted": 5.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 607, "output_tokens": 6, "latency_ms": 1312.1, "usd": 0.009555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "5", "compliant": true, "score": 1.0, "detail": { "predicted": 5.0, "expected": 5.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 607, "output_tokens": 6, "latency_ms": 1188.1, "usd": 0.009555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 607.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1241.8, "usd_sum": 0.028665 } }, { "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": 634, "output_tokens": 6, "latency_ms": 1496.3, "usd": 0.00996, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "poached", "compliant": true, "score": 1.0, "detail": { "predicted": "poached", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 6, "latency_ms": 947.8, "usd": 0.00996, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "poached", "compliant": true, "score": 1.0, "detail": { "predicted": "poached", "expected": "poached", "aliases": [] }, "metrics": { "input_tokens": 634, "output_tokens": 6, "latency_ms": 1100.2, "usd": 0.00996, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 634.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1181.433, "usd_sum": 0.02988 } }, { "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": 557, "output_tokens": 12, "latency_ms": 1089.6, "usd": 0.009255, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "aromatic_garnish", "compliant": true, "score": 1.0, "detail": { "predicted": "aromatic_garnish", "expected": "aromatic_garnish", "aliases": [] }, "metrics": { "input_tokens": 557, "output_tokens": 12, "latency_ms": 1006.5, "usd": 0.009255, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "aromatic_garnish", "compliant": true, "score": 1.0, "detail": { "predicted": "aromatic_garnish", "expected": "aromatic_garnish", "aliases": [] }, "metrics": { "input_tokens": 557, "output_tokens": 12, "latency_ms": 2277.5, "usd": 0.009255, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 557.0, "output_tokens_mean": 12.0, "latency_ms_mean": 1457.867, "usd_sum": 0.027765 } }, { "task_id": "ogs:core:benchmark-task:comp-015", "category": "composition", "capability": "component_set_identification", "difficulty": "hard", "cuisine_region": "thai", "scorer": "set_f1", "context_needs": [ "vocab.component_roles" ], "prompt_template_hash": "07976f0ee97244e5", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n---\n\nList the OGS component roles that appear in a classic Pad Thai (rice noodles, shrimp, tofu, egg, tamarind-palm sugar-fish sauce, bean sprouts, crushed peanuts, chives). Return a JSON array of role names.\n\nINPUT:\n{\n \"dish\": \"classic Pad Thai\"\n}\n\nANSWER FORMAT: set_of_roles", "expected": { "values": [ "starch", "main_protein", "acid_component", "seasoning", "aromatic_garnish", "textural_element", "fat_component" ] }, "samples": [ { "sample": 0, "raw_response": "[\"main_protein\",\"starch\",\"sauce\",\"acid_component\",\"aromatic_garnish\",\"textural_element\"]", "compliant": true, "score": 0.7692, "detail": { "predicted": [ "acid_component", "aromatic_garnish", "main_protein", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.8333, "recall": 0.7143 }, "metrics": { "input_tokens": 540, "output_tokens": 38, "latency_ms": 1451.7, "usd": 0.01095, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"main_protein\",\"starch\",\"sauce\",\"acid_component\",\"main_vegetable\",\"aromatic_garnish\",\"textural_element\"]", "compliant": true, "score": 0.7143, "detail": { "predicted": [ "acid_component", "aromatic_garnish", "main_protein", "main_vegetable", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.7143, "recall": 0.7143 }, "metrics": { "input_tokens": 540, "output_tokens": 45, "latency_ms": 1447.8, "usd": 0.011475, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"main_protein\",\"starch\",\"sauce\",\"acid_component\",\"aromatic_garnish\",\"textural_element\",\"main_vegetable\"]", "compliant": true, "score": 0.7143, "detail": { "predicted": [ "acid_component", "aromatic_garnish", "main_protein", "main_vegetable", "sauce", "starch", "textural_element" ], "expected": [ "acid_component", "aromatic_garnish", "fat_component", "main_protein", "seasoning", "starch", "textural_element" ], "precision": 0.7143, "recall": 0.7143 }, "metrics": { "input_tokens": 540, "output_tokens": 45, "latency_ms": 1396.0, "usd": 0.011475, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.7326, "score_summary": { "mean": 0.7326, "stdev": 0.0317, "sem": 0.0183, "ci95_lo": 0.6967, "ci95_hi": 0.7685, "n": 3 }, "score_if_valid": 0.7326, "format_rate": 1.0, "metrics": { "input_tokens_mean": 540.0, "output_tokens_mean": 42.667, "latency_ms_mean": 1431.833, "usd_sum": 0.0339 } }, { "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": 504, "output_tokens": 6, "latency_ms": 1083.3, "usd": 0.00801, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 504, "output_tokens": 6, "latency_ms": 1416.8, "usd": 0.00801, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 504, "output_tokens": 6, "latency_ms": 1117.3, "usd": 0.00801, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 504.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1205.8, "usd_sum": 0.02403 } }, { "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": 641, "output_tokens": 7, "latency_ms": 1205.2, "usd": 0.01014, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 641, "output_tokens": 7, "latency_ms": 964.0, "usd": 0.01014, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 641, "output_tokens": 7, "latency_ms": 1058.3, "usd": 0.01014, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 7.0, "latency_ms_mean": 1075.833, "usd_sum": 0.03042 } }, { "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": 544, "output_tokens": 8, "latency_ms": 1439.9, "usd": 0.00876, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "fat_component", "compliant": true, "score": 1.0, "detail": { "predicted": "fat_component", "expected": "fat_component", "aliases": [] }, "metrics": { "input_tokens": 544, "output_tokens": 8, "latency_ms": 1294.8, "usd": 0.00876, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "fat_component", "compliant": true, "score": 1.0, "detail": { "predicted": "fat_component", "expected": "fat_component", "aliases": [] }, "metrics": { "input_tokens": 544, "output_tokens": 8, "latency_ms": 1135.9, "usd": 0.00876, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 544.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1290.2, "usd_sum": 0.02628 } }, { "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": 498, "output_tokens": 6, "latency_ms": 1573.5, "usd": 0.00792, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 498, "output_tokens": 6, "latency_ms": 1176.5, "usd": 0.00792, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "cold", "compliant": true, "score": 1.0, "detail": { "predicted": "cold", "expected": "cold", "aliases": [] }, "metrics": { "input_tokens": 498, "output_tokens": 6, "latency_ms": 974.5, "usd": 0.00792, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 498.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1241.5, "usd_sum": 0.02376 } }, { "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": 647, "output_tokens": 6, "latency_ms": 1469.0, "usd": 0.010155, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 647, "output_tokens": 6, "latency_ms": 1124.4, "usd": 0.010155, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "4", "compliant": true, "score": 1.0, "detail": { "predicted": 4.0, "expected": 4.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 647, "output_tokens": 6, "latency_ms": 1074.3, "usd": 0.010155, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 647.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1222.567, "usd_sum": 0.030465 } }, { "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": 1456, "output_tokens": 5, "latency_ms": 916.7, "usd": 0.022215, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 1456, "output_tokens": 5, "latency_ms": 1025.3, "usd": 0.022215, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 1456, "output_tokens": 5, "latency_ms": 1104.2, "usd": 0.022215, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1456.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1015.4, "usd_sum": 0.066645 } }, { "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": 1523, "output_tokens": 15, "latency_ms": 1045.9, "usd": 0.02397, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1523, "output_tokens": 15, "latency_ms": 1148.2, "usd": 0.02397, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1523, "output_tokens": 15, "latency_ms": 1268.5, "usd": 0.02397, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1523.0, "output_tokens_mean": 15.0, "latency_ms_mean": 1154.2, "usd_sum": 0.07191 } }, { "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": 1438, "output_tokens": 5, "latency_ms": 1123.0, "usd": 0.021945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 1438, "output_tokens": 5, "latency_ms": 904.3, "usd": 0.021945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "no", "compliant": true, "score": 1.0, "detail": { "predicted": "no", "expected": "no", "aliases": [] }, "metrics": { "input_tokens": 1438, "output_tokens": 5, "latency_ms": 929.0, "usd": 0.021945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1438.0, "output_tokens_mean": 5.0, "latency_ms_mean": 985.433, "usd_sum": 0.065835 } }, { "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": 1439, "output_tokens": 13, "latency_ms": 1310.1, "usd": 0.02256, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1439, "output_tokens": 13, "latency_ms": 1162.8, "usd": 0.02256, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1439, "output_tokens": 13, "latency_ms": 1291.2, "usd": 0.02256, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1439.0, "output_tokens_mean": 13.0, "latency_ms_mean": 1254.7, "usd_sum": 0.06768 } }, { "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", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "milk" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 0.5 }, "metrics": { "input_tokens": 1499, "output_tokens": 6, "latency_ms": 1185.6, "usd": 0.022935, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "milk", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "milk" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 0.5 }, "metrics": { "input_tokens": 1499, "output_tokens": 6, "latency_ms": 927.9, "usd": 0.022935, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "milk", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "milk" ], "expected": [ "milk", "tree_nuts" ], "precision": 1.0, "recall": 0.5 }, "metrics": { "input_tokens": 1499, "output_tokens": 6, "latency_ms": 1514.1, "usd": 0.022935, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1499.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1209.2, "usd_sum": 0.068805 } }, { "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": 1442, "output_tokens": 21, "latency_ms": 1363.2, "usd": 0.023205, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1442, "output_tokens": 21, "latency_ms": 1071.3, "usd": 0.023205, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1442, "output_tokens": 21, "latency_ms": 2322.5, "usd": 0.023205, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1442.0, "output_tokens_mean": 21.0, "latency_ms_mean": 1585.667, "usd_sum": 0.069615 } }, { "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": "silken tofu", "compliant": true, "score": 1.0, "detail": { "predicted": "silken tofu", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 1424, "output_tokens": 9, "latency_ms": 1068.6, "usd": 0.022035, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "silken tofu", "compliant": true, "score": 1.0, "detail": { "predicted": "silken tofu", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 1424, "output_tokens": 9, "latency_ms": 1471.3, "usd": 0.022035, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "silken tofu", "compliant": true, "score": 1.0, "detail": { "predicted": "silken tofu", "expected": "silken tofu", "aliases": [ "silken tofu blended with nutritional yeast", "soft tofu" ] }, "metrics": { "input_tokens": 1424, "output_tokens": 9, "latency_ms": 1312.3, "usd": 0.022035, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1424.0, "output_tokens_mean": 9.0, "latency_ms_mean": 1284.067, "usd_sum": 0.066105 } }, { "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": 1397, "output_tokens": 6, "latency_ms": 1127.9, "usd": 0.021405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1397, "output_tokens": 6, "latency_ms": 1649.0, "usd": 0.021405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1397, "output_tokens": 6, "latency_ms": 1401.2, "usd": 0.021405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1397.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1392.7, "usd_sum": 0.064215 } }, { "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": 1554, "output_tokens": 39, "latency_ms": 1400.2, "usd": 0.026235, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1554, "output_tokens": 39, "latency_ms": 1442.5, "usd": 0.026235, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1554, "output_tokens": 39, "latency_ms": 7143.7, "usd": 0.026235, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1554.0, "output_tokens_mean": 39.0, "latency_ms_mean": 3328.8, "usd_sum": 0.078705 } }, { "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,fish,molluscs", "compliant": true, "score": 1.0, "detail": { "predicted": [ "cereals_containing_gluten", "fish", "molluscs" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1471, "output_tokens": 22, "latency_ms": 1325.7, "usd": 0.023715, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "cereals_containing_gluten,fish,molluscs", "compliant": true, "score": 1.0, "detail": { "predicted": [ "cereals_containing_gluten", "fish", "molluscs" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1471, "output_tokens": 22, "latency_ms": 905.0, "usd": 0.023715, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "cereals_containing_gluten,fish,molluscs", "compliant": true, "score": 1.0, "detail": { "predicted": [ "cereals_containing_gluten", "fish", "molluscs" ], "expected": [ "cereals_containing_gluten", "fish", "molluscs" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1471, "output_tokens": 22, "latency_ms": 1338.5, "usd": 0.023715, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1471.0, "output_tokens_mean": 22.0, "latency_ms_mean": 1189.733, "usd_sum": 0.071145 } }, { "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": 1514, "output_tokens": 17, "latency_ms": 1301.0, "usd": 0.023985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1514, "output_tokens": 17, "latency_ms": 1783.9, "usd": 0.023985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1514, "output_tokens": 17, "latency_ms": 1390.6, "usd": 0.023985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1514.0, "output_tokens_mean": 17.0, "latency_ms_mean": 1491.833, "usd_sum": 0.071955 } }, { "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": 1438, "output_tokens": 9, "latency_ms": 1218.3, "usd": 0.022245, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "pescatarian", "compliant": true, "score": 1.0, "detail": { "predicted": [ "pescatarian" ], "expected": [ "pescatarian" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1438, "output_tokens": 9, "latency_ms": 1442.2, "usd": 0.022245, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "pescatarian", "compliant": true, "score": 1.0, "detail": { "predicted": [ "pescatarian" ], "expected": [ "pescatarian" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 1438, "output_tokens": 9, "latency_ms": 1016.3, "usd": 0.022245, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1438.0, "output_tokens_mean": 9.0, "latency_ms_mean": 1225.6, "usd_sum": 0.066735 } }, { "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": 795, "output_tokens": 5, "latency_ms": 1270.1, "usd": 0.0123, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 795, "output_tokens": 5, "latency_ms": 984.9, "usd": 0.0123, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "star", "compliant": true, "score": 1.0, "detail": { "predicted": "star", "expected": "star", "aliases": [] }, "metrics": { "input_tokens": 795, "output_tokens": 5, "latency_ms": 937.2, "usd": 0.0123, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 795.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1064.067, "usd_sum": 0.0369 } }, { "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": 767, "output_tokens": 9, "latency_ms": 3072.9, "usd": 0.01218, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 767, "output_tokens": 9, "latency_ms": 1034.6, "usd": 0.01218, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "plowhorse", "compliant": true, "score": 1.0, "detail": { "predicted": "plowhorse", "expected": "plowhorse", "aliases": [] }, "metrics": { "input_tokens": 767, "output_tokens": 9, "latency_ms": 903.1, "usd": 0.01218, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 767.0, "output_tokens_mean": 9.0, "latency_ms_mean": 1670.2, "usd_sum": 0.03654 } }, { "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": 765, "output_tokens": 8, "latency_ms": 957.5, "usd": 0.012075, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 765, "output_tokens": 8, "latency_ms": 1065.6, "usd": 0.012075, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "puzzle", "compliant": true, "score": 1.0, "detail": { "predicted": "puzzle", "expected": "puzzle", "aliases": [] }, "metrics": { "input_tokens": 765, "output_tokens": 8, "latency_ms": 1070.0, "usd": 0.012075, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 765.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1031.033, "usd_sum": 0.036225 } }, { "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": 769, "output_tokens": 6, "latency_ms": 1363.7, "usd": 0.011985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 769, "output_tokens": 6, "latency_ms": 1171.7, "usd": 0.011985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "dog", "compliant": true, "score": 1.0, "detail": { "predicted": "dog", "expected": "dog", "aliases": [] }, "metrics": { "input_tokens": 769, "output_tokens": 6, "latency_ms": 1134.5, "usd": 0.011985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 769.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1223.3, "usd_sum": 0.035955 } }, { "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": 777, "output_tokens": 6, "latency_ms": 979.8, "usd": 0.012105, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "30", "compliant": true, "score": 1.0, "detail": { "predicted": 30.0, "expected": 30.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 777, "output_tokens": 6, "latency_ms": 934.1, "usd": 0.012105, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "30", "compliant": true, "score": 1.0, "detail": { "predicted": 30.0, "expected": 30.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 777, "output_tokens": 6, "latency_ms": 1821.6, "usd": 0.012105, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 777.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1245.167, "usd_sum": 0.036315 } }, { "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": 784, "output_tokens": 8, "latency_ms": 2261.4, "usd": 0.01236, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "15.50", "compliant": true, "score": 1.0, "detail": { "predicted": 15.5, "expected": 15.5, "tolerance": 0.05 }, "metrics": { "input_tokens": 784, "output_tokens": 8, "latency_ms": 1171.1, "usd": 0.01236, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "15.50", "compliant": true, "score": 1.0, "detail": { "predicted": 15.5, "expected": 15.5, "tolerance": 0.05 }, "metrics": { "input_tokens": 784, "output_tokens": 8, "latency_ms": 1388.4, "usd": 0.01236, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 784.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1606.967, "usd_sum": 0.03708 } }, { "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": 1000, "output_tokens": 5, "latency_ms": 1141.8, "usd": 0.015375, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 1000, "output_tokens": 5, "latency_ms": 916.0, "usd": 0.015375, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "C", "compliant": true, "score": 1.0, "detail": { "predicted": "c", "expected": "c", "aliases": [] }, "metrics": { "input_tokens": 1000, "output_tokens": 5, "latency_ms": 3092.2, "usd": 0.015375, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 5.0, "latency_ms_mean": 1716.667, "usd_sum": 0.046125 } }, { "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": 788, "output_tokens": 8, "latency_ms": 975.0, "usd": 0.01242, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "14.00", "compliant": true, "score": 1.0, "detail": { "predicted": 14.0, "expected": 14.0, "tolerance": 0.05 }, "metrics": { "input_tokens": 788, "output_tokens": 8, "latency_ms": 3317.4, "usd": 0.01242, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "14.00", "compliant": true, "score": 1.0, "detail": { "predicted": 14.0, "expected": 14.0, "tolerance": 0.05 }, "metrics": { "input_tokens": 788, "output_tokens": 8, "latency_ms": 1166.5, "usd": 0.01242, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 788.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1819.633, "usd_sum": 0.03726 } }, { "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": "**Weakness 1 — Structural monotony via orange purée repetition.** Four of the five courses lean on a sweet, starchy orange purée (pumpkin velouté, butternut risotto, pumpkin scallop purée, sweet potato main, pumpkin cheesecake). This flattens the intensity arc of the menu: every course delivers the same soft texture, the same carotenoid sweetness, and the same autumn-cliché aromatic register. A tasting menu should build contrast across courses — acid, bitterness, crunch, savoury depth — and here the guest effectively eats squash five times. Concrete change: replace the scallop course's pumpkin purée with a celeriac-and-brown-butter emulsion plus a sharp apple-verjus gastrique. This keeps the seasonal logic, re-introduces acidity and bitterness, and breaks the purée monotony without touching the signature scallop–pancetta pairing.\n\n**Weakness 2 — The nut-free path is non-trivially broken.** Amaretti (course 2) are built on bitter/sweet almonds, and the dessert's pecan brittle is an obvious tree-nut hazard; that's two of five courses requiring substitution, and amaretti crumble in particular is often overlooked because guests read \"cookie\" rather than \"nut.\" Under EU 1169/2011 both must be declared as `tree_nuts`, and a credible nut-free path needs pre-designed swaps, not line-level improvisation. Concrete change: specify a nut-free amaretti alternative (e.g. a toasted-oat and brown-butter streusel) and swap the pecan brittle for a caramelised pumpkin-seed brittle — same textural role, same visual, zero tree-nut exposure, and it reinforces the autumn theme.\n\n**Weakness 3 — Cost-to-price ratio risk on the scallop course against a 30% food-cost target.** Hand-dived scallops plus pancetta is the highest-cost plate on the menu and sits in the fish slot where portion count is fixed; at current wholesale, three U10 scallops alone often push that single course past 35–40% food cost, dragging the menu average above target even if the pork and dessert run lean. Combined with the vegetarian-path requirement (which forces a parallel prep line and usually a lower-margin substitution), the margin headroom is thin. Concrete change: re-engineer the fish course as two smaller seared scallops with a roasted-cauliflower and brown-butter base, where the vegetarian version simply omits the scallops and doubles the cauliflower — this lowers protein cost ~25%, simplifies the vegetarian path to a true mirror plate, and protects the 30% blended food-cost target.", "compliant": true, "score": 1.0, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies multiple concrete weaknesses: repeated pumpkin/squash monotony, nut-allergen blockage, and texture/starch heaviness, plus a plausible food-cost concern." }, { "id": "remediation", "weight": 0.3, "score": 1.0, "note": "It proposes specific, actionable substitutions with named ingredients and techniques that directly address the cited issues." }, { "id": "justification", "weight": 0.3, "score": 1.0, "note": "The reasoning is mechanism-based, citing intensity arc, texture contrast, allergen declaration/cross-contact planning, and food-cost percentage effects rather than generic praise." } ], "summary": "The candidate fully complies with the requested format by delivering three short paragraphs, each pairing a concrete critique with a specific fix and justification. It strongly matches the rubric by diagnosing major menu flaws, offering practical seasonal remedies, and grounding its reasoning in structural balance, allergen management, and cost mechanics.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 2005, "output_tokens": 898, "latency_ms": 18822.8, "usd": 0.097425, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "**Weakness 1 – Structural monotony from orange purée overload.** Four of the five courses lean on a soft, sweet, orange-fleshed squash or tuber purée (pumpkin velouté, butternut risotto, pumpkin purée under the scallops, sweet potato purée under the pork), and the dessert returns to pumpkin a fifth time. The guest experiences the same textural register (smooth, starchy, sweet-vegetal) and the same chromatic palette from amuse to dessert, which flattens progression and makes the scallop course taste like a reprise of the appetizer rather than a pivot. Concrete change: replace the pumpkin purée under the scallops with a celeriac-and-brown-butter purée plus a sharp apple-verjus gel — still autumnal, but it introduces a new root, a clean acid, and a pale colour that resets the eye before the pork.\n\n**Weakness 2 – Allergen and dietary path are not viable as written.** The brief requires a workable nut-free AND vegetarian route, but the appetizer's amaretti crumble carries `tree_nuts` (amaretti traditionally contain almond or apricot kernel), the dessert's pecan brittle is explicitly `tree_nuts`, and the fish and main courses offer no vegetarian substitution at all — a vegetarian guest eats squash velouté, squash risotto, and then a cheesecake, which is both monotonous and nutritionally thin. Concrete change: swap the amaretti crumble for a toasted pumpkin-seed and amaretto-free sablé (keeps the bitter-almond note via a drop of natural bitter-almond extract declared separately, or simply via brown-butter breadcrumb), and build a parallel vegetarian fish-course (hen-of-the-woods mushroom, brown butter, capers) and vegetarian main (roast celeriac \"steak\", cider jus stays identical) so both paths are genuinely five courses.\n\n**Weakness 3 – Cost-to-price ratio is skewed by the scallop course.** Against a 30% target food cost, pan-seared scallops with pancetta is almost certainly the most expensive plate on the menu while three of the other four courses are built on sub-€1 squash — meaning the menu's blended food-cost percentage is being dragged up by one dish while the others are quietly over-margined (likely Plowhorse behaviour for scallops, Puzzle/Star for the squash plates). Concrete change: reduce the scallop count from three to two and plate them over the new celeriac purée with a pancetta crumb rather than slices, which drops portion cost roughly 25–30% and re-centres the menu near the 30% target without the guest perceiving a downgrade, since the celeriac-apple pairing actually reads as more refined than pumpkin-pancetta.", "compliant": true, "score": 1.0, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies multiple concrete weaknesses: repeated pumpkin/squash across nearly every course, nut-allergen exposure, lack of a viable vegetarian path, structural puree/starch monotony, and scallop cost pressure." }, { "id": "remediation", "weight": 0.3, "score": 1.0, "note": "It proposes specific, actionable substitutions and parallel dishes, including celeriac purée with apple-verjus gel and named vegetarian replacements that directly address the diagnosed issues." }, { "id": "justification", "weight": 0.3, "score": 1.0, "note": "The reasoning is mechanism-based, citing palate progression, textural repetition, allergen exposure, dietary viability, and food-cost percentage effects rather than generic praise." } ], "summary": "The candidate fully complies with the requested format and delivers three short critique paragraphs without generic praise. It diagnoses several defensible menu flaws, offers concrete seasonal fixes, and justifies them using structural balance, allergen management, and cost mechanics.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 2005, "output_tokens": 930, "latency_ms": 19615.2, "usd": 0.099825, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "**Weakness 1 — Structural monotony via squash/pumpkin repetition.** Four of the five courses lean on pumpkin or butternut squash purée textures (velouté, risotto, scallop garnish, cheesecake). That is a structural_balance failure: the guest encounters the same sweet, orange, starchy purée four times, and the palate fatigues before the main course even arrives. Worse, three consecutive courses (amuse, appetizer, fish) are soft/creamy textures with no acid_component or textural contrast until the pancetta appears.\n\n**Weakness 2 — Allergen and dietary path is not viable as written.** The brief demands a workable nut-free route, but the appetizer's amaretti crumble is built on tree_nuts (almond) and the dessert leads with spiced pecan brittle — that is two of five courses requiring reformulation for a nut_free guest, not a simple swap. The vegetarian path is also thin: removing scallops/pancetta from course 3 and pork from course 4 leaves the guest eating a third squash purée course and then... what? There is no designed vegetarian main, only a subtraction.\n\n**Concrete change — rebuild courses 3 and 4 to introduce a bridge and genuine alternatives.** Replace the scallop course with a celeriac and wild mushroom course (roasted celeriac, mushroom XO, brown-butter hazelnut — or sunflower seed for the nut_free path) to break the orange-purée chain with an earthy, umami, acidic register. Keep the pork loin but design a parallel vegetarian main (e.g., stuffed delicata with lentils and cider-braised cabbage) so the vegetarian path has a real centerpiece rather than a gap. Finally, swap the amaretti crumble for an oat-spice streusel and offer a poached-pear alternative to the pecan brittle dessert — both preserve the autumn register while making the nut_free path a single clean substitution instead of two reformulations, and likely improve food cost percentage on the appetizer and dessert toward the 30% target.", "compliant": true, "score": 1.0, "detail": { "per_criterion": [ { "id": "diagnosis", "weight": 0.4, "score": 1.0, "note": "It clearly identifies multiple concrete weaknesses: repeated pumpkin/squash across four courses, heavy soft purée/starch sequencing, and nut-allergen plus weak vegetarian-path issues." }, { "id": "remediation", "weight": 0.3, "score": 1.0, "note": "It proposes specific, actionable substitutions with named dishes and ingredients that directly break monotony and improve dietary viability." }, { "id": "justification", "weight": 0.3, "score": 1.0, "note": "The reasoning is mechanism-based, citing structural balance, palate fatigue, textural contrast, allergen exposure, and food-cost implications rather than generic praise." } ], "summary": "The answer follows the requested free-text format and delivers three short paragraphs. It diagnoses several defensible menu-design problems and offers concrete, seasonally plausible fixes with clear OGS-style justification.", "judge_model": "gpt-5.4", "judge_prompt_hash": "756db6a487714bca", "judge_validated": false }, "metrics": { "input_tokens": 2005, "output_tokens": 682, "latency_ms": 14186.6, "usd": 0.081225, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2005.0, "output_tokens_mean": 836.667, "latency_ms_mean": 17541.533, "usd_sum": 0.278475 } }, { "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": 552, "output_tokens": 6, "latency_ms": 947.6, "usd": 0.00873, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 552, "output_tokens": 6, "latency_ms": 4780.3, "usd": 0.00873, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "herb", "compliant": true, "score": 1.0, "detail": { "predicted": "herb", "expected": "herb", "aliases": [ "spice" ] }, "metrics": { "input_tokens": 552, "output_tokens": 6, "latency_ms": 916.7, "usd": 0.00873, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 552.0, "output_tokens_mean": 6.0, "latency_ms_mean": 2214.867, "usd_sum": 0.02619 } }, { "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": 426, "output_tokens": 8, "latency_ms": 1164.1, "usd": 0.00699, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "الأردن", "compliant": true, "score": 1.0, "detail": { "predicted": "الأردن", "expected": "jordan", "aliases": [ "الأردن", "jordan (الأردن)" ] }, "metrics": { "input_tokens": 426, "output_tokens": 8, "latency_ms": 968.1, "usd": 0.00699, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "الأردن", "compliant": true, "score": 1.0, "detail": { "predicted": "الأردن", "expected": "jordan", "aliases": [ "الأردن", "jordan (الأردن)" ] }, "metrics": { "input_tokens": 426, "output_tokens": 8, "latency_ms": 1019.1, "usd": 0.00699, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 426.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1050.433, "usd_sum": 0.02097 } }, { "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": 423, "output_tokens": 8, "latency_ms": 3379.5, "usd": 0.006945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 423, "output_tokens": 8, "latency_ms": 1159.2, "usd": 0.006945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Galicia", "compliant": true, "score": 1.0, "detail": { "predicted": "galicia", "expected": "galicia", "aliases": [ "galícia", "galiza" ] }, "metrics": { "input_tokens": 423, "output_tokens": 8, "latency_ms": 1092.6, "usd": 0.006945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 8.0, "latency_ms_mean": 1877.1, "usd_sum": 0.020835 } }, { "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": 618, "output_tokens": 7, "latency_ms": 1250.7, "usd": 0.009795, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 618, "output_tokens": 7, "latency_ms": 1051.3, "usd": 0.009795, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 618, "output_tokens": 7, "latency_ms": 953.1, "usd": 0.009795, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 618.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1085.033, "usd_sum": 0.029385 } }, { "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": 428, "output_tokens": 8, "latency_ms": 1108.9, "usd": 0.00702, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 428, "output_tokens": 8, "latency_ms": 1162.8, "usd": 0.00702, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Marseille", "compliant": true, "score": 1.0, "detail": { "predicted": "marseille", "expected": "marseille", "aliases": [] }, "metrics": { "input_tokens": 428, "output_tokens": 8, "latency_ms": 1051.2, "usd": 0.00702, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 428.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1107.633, "usd_sum": 0.02106 } }, { "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": "[1.5,6,4,0.5,3]", "compliant": true, "score": 0.7333, "detail": { "per_position": [ { "index": 0, "predicted": 1.5, "expected": 1, "score": 0.6667 }, { "index": 1, "predicted": 6, "expected": 5, "score": 0.3333 }, { "index": 2, "predicted": 4, "expected": 4, "score": 1.0 }, { "index": 3, "predicted": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 3, "expected": 3, "score": 1.0 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 604, "output_tokens": 19, "latency_ms": 4300.3, "usd": 0.010485, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[1.5,6,4.5,0.5,3]", "compliant": true, "score": 0.6667, "detail": { "per_position": [ { "index": 0, "predicted": 1.5, "expected": 1, "score": 0.6667 }, { "index": 1, "predicted": 6, "expected": 5, "score": 0.3333 }, { "index": 2, "predicted": 4.5, "expected": 4, "score": 0.6667 }, { "index": 3, "predicted": 0.5, "expected": 1, "score": 0.6667 }, { "index": 4, "predicted": 3, "expected": 3, "score": 1.0 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 604, "output_tokens": 21, "latency_ms": 1862.9, "usd": 0.010635, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[2,6,4,1,3]", "compliant": true, "score": 0.7333, "detail": { "per_position": [ { "index": 0, "predicted": 2, "expected": 1, "score": 0.3333 }, { "index": 1, "predicted": 6, "expected": 5, "score": 0.3333 }, { "index": 2, "predicted": 4, "expected": 4, "score": 1.0 }, { "index": 3, "predicted": 1, "expected": 1, "score": 1.0 }, { "index": 4, "predicted": 3, "expected": 3, "score": 1.0 } ], "tolerance": 1.5 }, "metrics": { "input_tokens": 604, "output_tokens": 15, "latency_ms": 1373.9, "usd": 0.010185, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.7111, "score_summary": { "mean": 0.7111, "stdev": 0.0385, "sem": 0.0222, "ci95_lo": 0.6676, "ci95_hi": 0.7546, "n": 3 }, "score_if_valid": 0.7111, "format_rate": 1.0, "metrics": { "input_tokens_mean": 604.0, "output_tokens_mean": 18.333, "latency_ms_mean": 2512.367, "usd_sum": 0.031305 } }, { "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": 427, "output_tokens": 8, "latency_ms": 963.3, "usd": 0.007005, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 427, "output_tokens": 8, "latency_ms": 1034.7, "usd": 0.007005, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Toscana", "compliant": true, "score": 1.0, "detail": { "predicted": "toscana", "expected": "toscana", "aliases": [] }, "metrics": { "input_tokens": 427, "output_tokens": 8, "latency_ms": 927.1, "usd": 0.007005, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 427.0, "output_tokens_mean": 8.0, "latency_ms_mean": 975.033, "usd_sum": 0.021015 } }, { "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": 523, "output_tokens": 7, "latency_ms": 1044.7, "usd": 0.00837, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 523, "output_tokens": 7, "latency_ms": 948.1, "usd": 0.00837, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "barolo", "compliant": true, "score": 1.0, "detail": { "predicted": "barolo", "expected": "barolo", "aliases": [] }, "metrics": { "input_tokens": 523, "output_tokens": 7, "latency_ms": 2573.0, "usd": 0.00837, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 523.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1521.933, "usd_sum": 0.02511 } }, { "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": 518, "output_tokens": 7, "latency_ms": 1174.0, "usd": 0.008295, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 518, "output_tokens": 7, "latency_ms": 1316.0, "usd": 0.008295, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 518, "output_tokens": 7, "latency_ms": 988.5, "usd": 0.008295, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 518.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1159.5, "usd_sum": 0.024885 } }, { "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": 529, "output_tokens": 6, "latency_ms": 1100.0, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 529, "output_tokens": 6, "latency_ms": 1417.5, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "sake", "compliant": true, "score": 1.0, "detail": { "predicted": "sake", "expected": "sake", "aliases": [] }, "metrics": { "input_tokens": 529, "output_tokens": 6, "latency_ms": 752.4, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 529.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1089.967, "usd_sum": 0.025155 } }, { "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": 1259, "output_tokens": 6, "latency_ms": 1176.0, "usd": 0.019335, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "375", "compliant": true, "score": 1.0, "detail": { "predicted": 375.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 1259, "output_tokens": 6, "latency_ms": 1786.6, "usd": 0.019335, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "375", "compliant": true, "score": 1.0, "detail": { "predicted": 375.0, "expected": 375.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 1259, "output_tokens": 6, "latency_ms": 1150.9, "usd": 0.019335, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1259.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1371.167, "usd_sum": 0.058005 } }, { "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": 1271, "output_tokens": 6, "latency_ms": 1023.4, "usd": 0.019515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "114", "compliant": true, "score": 1.0, "detail": { "predicted": 114.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 1271, "output_tokens": 6, "latency_ms": 1121.4, "usd": 0.019515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "114", "compliant": true, "score": 1.0, "detail": { "predicted": 114.0, "expected": 114.0, "tolerance": 5.0 }, "metrics": { "input_tokens": 1271, "output_tokens": 6, "latency_ms": 1194.6, "usd": 0.019515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1271.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1113.133, "usd_sum": 0.058545 } }, { "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": "75*8.84 + 25*0.20 = 663 + 5 = 668\n\n668", "compliant": true, "score": 0.0, "detail": { "predicted": 75.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 1277, "output_tokens": 32, "latency_ms": 2025.6, "usd": 0.021555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "75*8.84 + 25*0.20 = 663 + 5 = 668\n\n668", "compliant": true, "score": 0.0, "detail": { "predicted": 75.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 1277, "output_tokens": 32, "latency_ms": 1364.3, "usd": 0.021555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "75*8.84 + 25*0.20 = 663 + 5 = 668\n\n668", "compliant": true, "score": 0.0, "detail": { "predicted": 75.0, "expected": 668.0, "tolerance": 15.0 }, "metrics": { "input_tokens": 1277, "output_tokens": 32, "latency_ms": 1544.9, "usd": 0.021555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1277.0, "output_tokens_mean": 32.0, "latency_ms_mean": 1644.933, "usd_sum": 0.064665 } }, { "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": "Raw mass = 180/0.7 ≈ 257 g. Protein = 257 × 0.23 ≈ 59 g.\n\n59", "compliant": true, "score": 0.0, "detail": { "predicted": 180.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 1254, "output_tokens": 50, "latency_ms": 1539.7, "usd": 0.02256, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Raw mass = 180/0.7 ≈ 257g. Protein = 257 × 0.23 ≈ 59g.\n\n59", "compliant": true, "score": 0.0, "detail": { "predicted": 180.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 1254, "output_tokens": 48, "latency_ms": 1621.9, "usd": 0.02241, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Raw mass = 180 / 0.7 ≈ 257 g\nProtein = 257 × 0.23 ≈ 59 g\n\n59", "compliant": true, "score": 0.0, "detail": { "predicted": 180.0, "expected": 59.0, "tolerance": 4.0 }, "metrics": { "input_tokens": 1254, "output_tokens": 51, "latency_ms": 1679.1, "usd": 0.022635, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1254.0, "output_tokens_mean": 49.667, "latency_ms_mean": 1613.567, "usd_sum": 0.067605 } }, { "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": "Pasta: 85g → C: 63.75, P: 11.05, F: 1.275\nButter: 10g → C: 0.01, P: 0.09, F: 8.1\nParmesan: 15g → C: 0.48, P: 5.25, F: 4.35\n\nCarb: 63.75 + 0.01 + 0.48 = 64.24\nProtein: 11.05 + 0.09 + 5.25 = 16.39\nFat: 1.275 + 8.1 + 4.35 = 13.725\n\nkcal: 64.24*4 + 16.39*4 + 13.725*9 = 256.96 + 65.56 + 123.525 = 446.045 → 446\n\n[64.24, 16.39, 13.73, 446]", "compliant": true, "score": 0.985, "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": 13.73, "expected": 13.7, "score": 0.99 }, { "index": 3, "predicted": 446, "expected": 446, "score": 1.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 1345, "output_tokens": 248, "latency_ms": 5684.7, "usd": 0.038775, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Pasta (85g): C=63.75, P=11.05, F=1.275\nButter (10g): C=0.01, P=0.09, F=8.1\nParmesan (15g): C=0.48, P=5.25, F=4.35\n\nTotals: C=64.24, P=16.39, F=13.725\nkcal = 64.24*4 + 16.39*4 + 13.725*9 = 256.96 + 65.56 + 123.525 = 446.045 ≈ 446\n\n[64.24, 16.39, 13.73, 446]", "compliant": true, "score": 0.985, "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": 13.73, "expected": 13.7, "score": 0.99 }, { "index": 3, "predicted": 446, "expected": 446, "score": 1.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 1345, "output_tokens": 180, "latency_ms": 3768.4, "usd": 0.033675, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Pasta: 63.75 C, 11.05 P, 1.275 F\nButter: 0.01 C, 0.09 P, 8.1 F\nParmesan: 0.48 C, 5.25 P, 4.35 F\n\nTotals: C=64.24, P=16.39, F=13.725\nkcal = 4*64.24 + 4*16.39 + 9*13.725 = 256.96 + 65.56 + 123.525 = 446.045\n\n[64.24, 16.39, 13.73, 446]", "compliant": true, "score": 0.985, "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": 13.73, "expected": 13.7, "score": 0.99 }, { "index": 3, "predicted": 446, "expected": 446, "score": 1.0 } ], "tolerance": 3.0 }, "metrics": { "input_tokens": 1345, "output_tokens": 173, "latency_ms": 4290.1, "usd": 0.03315, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.985, "score_summary": { "mean": 0.985, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.985, "ci95_hi": 0.985, "n": 3 }, "score_if_valid": 0.985, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1345.0, "output_tokens_mean": 200.333, "latency_ms_mean": 4581.067, "usd_sum": 0.1056 } }, { "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": "OJ: 180g × 9g carb/100g = 16.2g carb × 4 = 64.8 kcal\nSugar: 12g × 4 = 48 kcal\nTotal: 112.8 → 113\n\n113", "compliant": true, "score": 0.0, "detail": { "predicted": 180.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 1252, "output_tokens": 75, "latency_ms": 2213.9, "usd": 0.024405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "OJ: 180 g × 9/100 = 16.2 g carbs → 64.8 kcal\nSugar: 12 g × 4 = 48 kcal\nTotal: 112.8 → 113\n\n113", "compliant": true, "score": 0.0, "detail": { "predicted": 180.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 1252, "output_tokens": 72, "latency_ms": 1905.4, "usd": 0.02418, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "OJ: 180g × 9% carb = 16.2g carb × 4 = 64.8 kcal\nSugar: 12g × 4 = 48 kcal\nTotal: 112.8 → 113\n\n113", "compliant": true, "score": 0.0, "detail": { "predicted": 180.0, "expected": 111.0, "tolerance": 6.0 }, "metrics": { "input_tokens": 1252, "output_tokens": 72, "latency_ms": 3459.5, "usd": 0.02418, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1252.0, "output_tokens_mean": 73.0, "latency_ms_mean": 2526.267, "usd_sum": 0.072765 } }, { "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": 1197, "output_tokens": 6, "latency_ms": 1053.0, "usd": 0.018405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.1 }, "metrics": { "input_tokens": 1197, "output_tokens": 6, "latency_ms": 1189.1, "usd": 0.018405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.1 }, "metrics": { "input_tokens": 1197, "output_tokens": 6, "latency_ms": 1232.7, "usd": 0.018405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1197.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1158.267, "usd_sum": 0.055215 } }, { "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": 1215, "output_tokens": 7, "latency_ms": 1248.1, "usd": 0.01875, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "1046", "compliant": true, "score": 1.0, "detail": { "predicted": 1046.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 1215, "output_tokens": 7, "latency_ms": 1097.8, "usd": 0.01875, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "1046", "compliant": true, "score": 1.0, "detail": { "predicted": 1046.0, "expected": 1046.0, "tolerance": 10.0 }, "metrics": { "input_tokens": 1215, "output_tokens": 7, "latency_ms": 1582.1, "usd": 0.01875, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1215.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1309.333, "usd_sum": 0.05625 } }, { "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": "Butter 100g: 0.1 C, 0.9 P, 81 F\nCream 150g: 4.2 C, 3 P, 55.5 F\nParmesan 60g: 1.92 C, 21 P, 17.4 F\n\nTotals: 6.22 C, 24.9 P, 153.9 F\n\nPer 100g (finished 250g): 2.488 C, 9.96 P, 61.56 F\nkcal: 2.488*4 + 9.96*4 + 61.56*9 = 9.952 + 39.84 + 554.04 = 603.8 ≈ 604\n\n[2.5, 10.0, 61.6, 604]", "compliant": true, "score": 0.475, "detail": { "per_position": [ { "index": 0, "predicted": 2.5, "expected": 2.5, "score": 1.0 }, { "index": 1, "predicted": 10.0, "expected": 9.6, "score": 0.9 }, { "index": 2, "predicted": 61.6, "expected": 55.2, "score": 0.0 }, { "index": 3, "predicted": 604, "expected": 545, "score": 0.0 } ], "tolerance": 4.0 }, "metrics": { "input_tokens": 1359, "output_tokens": 218, "latency_ms": 4598.0, "usd": 0.036735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Butter (100g): 0.1 C, 0.9 P, 81 F\nCream (150g): 4.2 C, 3 P, 55.5 F\nParmesan (60g): 1.92 C, 21 P, 17.4 F\n\nTotals: C=6.22, P=24.9, F=153.9\nPer 250g finished → per 100g: multiply by 100/250 = 0.4\n\nC: 2.488\nP: 9.96\nF: 61.56\nkcal: 2.488*4 + 9.96*4 + 61.56*9 = 9.952 + 39.84 + 554.04 = 603.83 → 604\n\n[2.49, 9.96, 61.56, 604]", "compliant": true, "score": 0.4769, "detail": { "per_position": [ { "index": 0, "predicted": 2.49, "expected": 2.5, "score": 0.9975 }, { "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": 1359, "output_tokens": 228, "latency_ms": 4346.8, "usd": 0.037485, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Butter (100g): 0.1 C, 0.9 P, 81 F\nCream (150g): 4.2 C, 3 P, 55.5 F\nParmesan (60g): 1.92 C, 21 P, 17.4 F\n\nTotals: C=6.22, P=24.9, F=153.9\nPer 100g finished (÷2.5): C=2.488, P=9.96, F=61.56\nkcal = 4*2.488 + 4*9.96 + 9*61.56 = 9.952 + 39.84 + 554.04 = 603.83 → 604\n\n[2.49, 9.96, 61.56, 604]", "compliant": true, "score": 0.4769, "detail": { "per_position": [ { "index": 0, "predicted": 2.49, "expected": 2.5, "score": 0.9975 }, { "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": 1359, "output_tokens": 211, "latency_ms": 3897.2, "usd": 0.03621, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.4763, "score_summary": { "mean": 0.4763, "stdev": 0.0011, "sem": 0.0006, "ci95_lo": 0.475, "ci95_hi": 0.4775, "n": 3 }, "score_if_valid": 0.4763, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1359.0, "output_tokens_mean": 219.0, "latency_ms_mean": 4280.667, "usd_sum": 0.11043 } }, { "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": 1256, "output_tokens": 8, "latency_ms": 1734.4, "usd": 0.01944, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "olive oil", "compliant": true, "score": 1.0, "detail": { "predicted": "olive oil", "expected": "olive oil", "aliases": [ "olive-oil" ] }, "metrics": { "input_tokens": 1256, "output_tokens": 8, "latency_ms": 1698.2, "usd": 0.01944, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "olive oil", "compliant": true, "score": 1.0, "detail": { "predicted": "olive oil", "expected": "olive oil", "aliases": [ "olive-oil" ] }, "metrics": { "input_tokens": 1256, "output_tokens": 8, "latency_ms": 1009.8, "usd": 0.01944, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1256.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1480.8, "usd_sum": 0.05832 } }, { "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": 604, "output_tokens": 5, "latency_ms": 1456.6, "usd": 0.009435, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 604, "output_tokens": 5, "latency_ms": 1736.0, "usd": 0.009435, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 604, "output_tokens": 5, "latency_ms": 988.6, "usd": 0.009435, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 604.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1393.733, "usd_sum": 0.028305 } }, { "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": 590, "output_tokens": 5, "latency_ms": 1350.0, "usd": 0.009225, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 590, "output_tokens": 5, "latency_ms": 1244.8, "usd": 0.009225, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 590, "output_tokens": 5, "latency_ms": 1219.0, "usd": 0.009225, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 590.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1271.267, "usd_sum": 0.027675 } }, { "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": 612, "output_tokens": 5, "latency_ms": 1680.3, "usd": 0.009555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 612, "output_tokens": 5, "latency_ms": 1135.5, "usd": 0.009555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 612, "output_tokens": 5, "latency_ms": 1018.9, "usd": 0.009555, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 612.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1278.233, "usd_sum": 0.028665 } }, { "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": 574, "output_tokens": 5, "latency_ms": 2034.4, "usd": 0.008985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 574, "output_tokens": 5, "latency_ms": 847.3, "usd": 0.008985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 574, "output_tokens": 5, "latency_ms": 1393.1, "usd": 0.008985, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 574.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1424.933, "usd_sum": 0.026955 } }, { "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": 580, "output_tokens": 5, "latency_ms": 1013.5, "usd": 0.009075, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 580, "output_tokens": 5, "latency_ms": 1041.0, "usd": 0.009075, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "b", "compliant": true, "score": 1.0, "detail": { "predicted": "b", "expected_best": "b", "rank": 0 }, "metrics": { "input_tokens": 580, "output_tokens": 5, "latency_ms": 1327.1, "usd": 0.009075, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 580.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1127.2, "usd_sum": 0.027225 } }, { "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": 586, "output_tokens": 5, "latency_ms": 881.1, "usd": 0.009165, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 586, "output_tokens": 5, "latency_ms": 1001.4, "usd": 0.009165, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 586, "output_tokens": 5, "latency_ms": 1143.1, "usd": 0.009165, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 586.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1008.533, "usd_sum": 0.027495 } }, { "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": 589, "output_tokens": 5, "latency_ms": 1061.4, "usd": 0.00921, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 589, "output_tokens": 5, "latency_ms": 1115.1, "usd": 0.00921, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 589, "output_tokens": 5, "latency_ms": 1027.4, "usd": 0.00921, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 589.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1067.967, "usd_sum": 0.02763 } }, { "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": 566, "output_tokens": 5, "latency_ms": 1110.9, "usd": 0.008865, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 566, "output_tokens": 5, "latency_ms": 890.2, "usd": 0.008865, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "D", "expected": "D", "aliases": [] }, "metrics": { "input_tokens": 566, "output_tokens": 5, "latency_ms": 1210.7, "usd": 0.008865, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 566.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1070.6, "usd_sum": 0.026595 } }, { "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": 598, "output_tokens": 5, "latency_ms": 865.8, "usd": 0.009345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 598, "output_tokens": 5, "latency_ms": 995.5, "usd": 0.009345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 598, "output_tokens": 5, "latency_ms": 1983.8, "usd": 0.009345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 598.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1281.7, "usd_sum": 0.028035 } }, { "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": 565, "output_tokens": 5, "latency_ms": 1012.8, "usd": 0.00885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 565, "output_tokens": 5, "latency_ms": 851.6, "usd": 0.00885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 565, "output_tokens": 5, "latency_ms": 1365.6, "usd": 0.00885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 565.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1076.667, "usd_sum": 0.02655 } }, { "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": 559, "output_tokens": 5, "latency_ms": 966.5, "usd": 0.00876, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 559, "output_tokens": 5, "latency_ms": 1189.4, "usd": 0.00876, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 559, "output_tokens": 5, "latency_ms": 2043.3, "usd": 0.00876, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 559.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1399.733, "usd_sum": 0.02628 } }, { "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": 578, "output_tokens": 5, "latency_ms": 1065.9, "usd": 0.009045, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 578, "output_tokens": 5, "latency_ms": 3099.4, "usd": 0.009045, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 578, "output_tokens": 5, "latency_ms": 861.3, "usd": 0.009045, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 578.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1675.533, "usd_sum": 0.027135 } }, { "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": 555, "output_tokens": 5, "latency_ms": 1176.3, "usd": 0.0087, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 555, "output_tokens": 5, "latency_ms": 960.3, "usd": 0.0087, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 555, "output_tokens": 5, "latency_ms": 1406.8, "usd": 0.0087, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 555.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1181.133, "usd_sum": 0.0261 } }, { "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": 564, "output_tokens": 5, "latency_ms": 935.9, "usd": 0.008835, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 564, "output_tokens": 5, "latency_ms": 1145.8, "usd": 0.008835, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 564, "output_tokens": 5, "latency_ms": 1236.4, "usd": 0.008835, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 564.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1106.033, "usd_sum": 0.026505 } }, { "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": 571, "output_tokens": 5, "latency_ms": 1159.1, "usd": 0.00894, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 571, "output_tokens": 5, "latency_ms": 940.7, "usd": 0.00894, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 571, "output_tokens": 5, "latency_ms": 1459.3, "usd": 0.00894, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 571.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1186.367, "usd_sum": 0.02682 } }, { "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": 606, "output_tokens": 5, "latency_ms": 1361.7, "usd": 0.009465, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 606, "output_tokens": 5, "latency_ms": 1003.4, "usd": 0.009465, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 606, "output_tokens": 5, "latency_ms": 931.0, "usd": 0.009465, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 606.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1098.7, "usd_sum": 0.028395 } }, { "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": 563, "output_tokens": 5, "latency_ms": 878.8, "usd": 0.00882, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 563, "output_tokens": 5, "latency_ms": 1018.6, "usd": 0.00882, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 563, "output_tokens": 5, "latency_ms": 1245.8, "usd": 0.00882, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 563.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1047.733, "usd_sum": 0.02646 } }, { "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": 583, "output_tokens": 5, "latency_ms": 900.0, "usd": 0.00912, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 583, "output_tokens": 5, "latency_ms": 891.1, "usd": 0.00912, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 583, "output_tokens": 5, "latency_ms": 970.1, "usd": 0.00912, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 583.0, "output_tokens_mean": 5.0, "latency_ms_mean": 920.4, "usd_sum": 0.02736 } }, { "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": 567, "output_tokens": 5, "latency_ms": 1175.4, "usd": 0.00888, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 567, "output_tokens": 5, "latency_ms": 8422.9, "usd": 0.00888, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "a", "compliant": true, "score": 1.0, "detail": { "predicted": "a", "expected_best": "a", "rank": 0 }, "metrics": { "input_tokens": 567, "output_tokens": 5, "latency_ms": 1190.4, "usd": 0.00888, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 567.0, "output_tokens_mean": 5.0, "latency_ms_mean": 3596.233, "usd_sum": 0.02664 } }, { "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": 546, "output_tokens": 6, "latency_ms": 1438.9, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 546, "output_tokens": 6, "latency_ms": 1079.3, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "A+", "compliant": true, "score": 1.0, "detail": { "predicted": "a+", "expected": "a+", "aliases": [] }, "metrics": { "input_tokens": 546, "output_tokens": 6, "latency_ms": 1184.6, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 546.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1234.267, "usd_sum": 0.02592 } }, { "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": 396, "output_tokens": 11, "latency_ms": 1213.0, "usd": 0.006765, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 396, "output_tokens": 11, "latency_ms": 970.8, "usd": 0.006765, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 396, "output_tokens": 11, "latency_ms": 1062.7, "usd": 0.006765, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 396.0, "output_tokens_mean": 11.0, "latency_ms_mean": 1082.167, "usd_sum": 0.020295 } }, { "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": 389, "output_tokens": 10, "latency_ms": 1149.4, "usd": 0.006585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 389, "output_tokens": 10, "latency_ms": 1199.4, "usd": 0.006585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Chardonnay", "compliant": true, "score": 1.0, "detail": { "predicted": "chardonnay", "expected": "chardonnay", "aliases": [] }, "metrics": { "input_tokens": 389, "output_tokens": 10, "latency_ms": 1083.1, "usd": 0.006585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 10.0, "latency_ms_mean": 1143.967, "usd_sum": 0.019755 } }, { "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": 381, "output_tokens": 9, "latency_ms": 1362.7, "usd": 0.00639, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 381, "output_tokens": 9, "latency_ms": 2022.1, "usd": 0.00639, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Vietnam", "compliant": true, "score": 1.0, "detail": { "predicted": "vietnam", "expected": "vietnam", "aliases": [] }, "metrics": { "input_tokens": 381, "output_tokens": 9, "latency_ms": 1346.8, "usd": 0.00639, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 381.0, "output_tokens_mean": 9.0, "latency_ms_mean": 1577.2, "usd_sum": 0.01917 } }, { "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": "Gewürztraminer", "compliant": true, "score": 0.0, "detail": { "predicted": "gewürztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 404, "output_tokens": 12, "latency_ms": 1130.6, "usd": 0.00696, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Gewürztraminer", "compliant": true, "score": 0.0, "detail": { "predicted": "gewürztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 404, "output_tokens": 12, "latency_ms": 1138.1, "usd": 0.00696, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Gewürztraminer", "compliant": true, "score": 0.0, "detail": { "predicted": "gewürztraminer", "expected": "gewurztraminer", "aliases": [] }, "metrics": { "input_tokens": 404, "output_tokens": 12, "latency_ms": 1149.3, "usd": 0.00696, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 404.0, "output_tokens_mean": 12.0, "latency_ms_mean": 1139.333, "usd_sum": 0.02088 } }, { "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": 412, "output_tokens": 8, "latency_ms": 1102.5, "usd": 0.00678, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 412, "output_tokens": 8, "latency_ms": 945.4, "usd": 0.00678, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "espagnole", "compliant": true, "score": 1.0, "detail": { "predicted": "espagnole", "expected": "espagnole", "aliases": [] }, "metrics": { "input_tokens": 412, "output_tokens": 8, "latency_ms": 1429.5, "usd": 0.00678, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 412.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1159.133, "usd_sum": 0.02034 } }, { "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": 461, "output_tokens": 8, "latency_ms": 1008.1, "usd": 0.007515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 461, "output_tokens": 8, "latency_ms": 3607.5, "usd": 0.007515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Reserva", "compliant": true, "score": 1.0, "detail": { "predicted": "reserva", "expected": "reserva", "aliases": [] }, "metrics": { "input_tokens": 461, "output_tokens": 8, "latency_ms": 994.4, "usd": 0.007515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 461.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1870.0, "usd_sum": 0.022545 } }, { "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": 408, "output_tokens": 7, "latency_ms": 1242.7, "usd": 0.006645, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 408, "output_tokens": 7, "latency_ms": 1220.8, "usd": 0.006645, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Korea", "compliant": true, "score": 1.0, "detail": { "predicted": "korea", "expected": "korea", "aliases": [ "south korea", "republic of korea" ] }, "metrics": { "input_tokens": 408, "output_tokens": 7, "latency_ms": 1111.1, "usd": 0.006645, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 7.0, "latency_ms_mean": 1191.533, "usd_sum": 0.019935 } }, { "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": 413, "output_tokens": 11, "latency_ms": 957.9, "usd": 0.00702, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 413, "output_tokens": 11, "latency_ms": 1264.1, "usd": 0.00702, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Nebbiolo", "compliant": true, "score": 1.0, "detail": { "predicted": "nebbiolo", "expected": "nebbiolo", "aliases": [] }, "metrics": { "input_tokens": 413, "output_tokens": 11, "latency_ms": 2351.5, "usd": 0.00702, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 413.0, "output_tokens_mean": 11.0, "latency_ms_mean": 1524.5, "usd_sum": 0.02106 } }, { "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": 413, "output_tokens": 7, "latency_ms": 1130.9, "usd": 0.00672, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 413, "output_tokens": 7, "latency_ms": 1006.3, "usd": 0.00672, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Peru", "compliant": true, "score": 1.0, "detail": { "predicted": "peru", "expected": "peru", "aliases": [] }, "metrics": { "input_tokens": 413, "output_tokens": 7, "latency_ms": 1377.1, "usd": 0.00672, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 413.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1171.433, "usd_sum": 0.02016 } }, { "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": 409, "output_tokens": 7, "latency_ms": 1024.4, "usd": 0.00666, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 409, "output_tokens": 7, "latency_ms": 1080.7, "usd": 0.00666, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Spain", "compliant": true, "score": 1.0, "detail": { "predicted": "spain", "expected": "spain", "aliases": [] }, "metrics": { "input_tokens": 409, "output_tokens": 7, "latency_ms": 1124.0, "usd": 0.00666, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 7.0, "latency_ms_mean": 1076.367, "usd_sum": 0.01998 } }, { "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": 424, "output_tokens": 8, "latency_ms": 1385.7, "usd": 0.00696, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Chablis", "compliant": true, "score": 1.0, "detail": { "predicted": "chablis", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 424, "output_tokens": 8, "latency_ms": 963.9, "usd": 0.00696, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Chablis", "compliant": true, "score": 1.0, "detail": { "predicted": "chablis", "expected": "chablis", "aliases": [ "muscadet" ] }, "metrics": { "input_tokens": 424, "output_tokens": 8, "latency_ms": 1535.4, "usd": 0.00696, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 424.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1295.0, "usd_sum": 0.02088 } }, { "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": 434, "output_tokens": 9, "latency_ms": 1089.8, "usd": 0.007185, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 434, "output_tokens": 10, "latency_ms": 792.6, "usd": 0.00726, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "hollandaise", "compliant": true, "score": 1.0, "detail": { "predicted": "hollandaise", "expected": "hollandaise", "aliases": [] }, "metrics": { "input_tokens": 434, "output_tokens": 9, "latency_ms": 1116.6, "usd": 0.007185, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 434.0, "output_tokens_mean": 9.333, "latency_ms_mean": 999.667, "usd_sum": 0.02163 } }, { "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": 403, "output_tokens": 7, "latency_ms": 1594.9, "usd": 0.00657, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 403, "output_tokens": 7, "latency_ms": 945.1, "usd": 0.00657, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Japan", "compliant": true, "score": 1.0, "detail": { "predicted": "japan", "expected": "japan", "aliases": [] }, "metrics": { "input_tokens": 403, "output_tokens": 7, "latency_ms": 1002.2, "usd": 0.00657, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 7.0, "latency_ms_mean": 1180.733, "usd_sum": 0.01971 } }, { "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": 419, "output_tokens": 8, "latency_ms": 1175.6, "usd": 0.006885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 419, "output_tokens": 8, "latency_ms": 938.4, "usd": 0.006885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Morocco", "compliant": true, "score": 1.0, "detail": { "predicted": "morocco", "expected": "morocco", "aliases": [] }, "metrics": { "input_tokens": 419, "output_tokens": 8, "latency_ms": 1048.6, "usd": 0.006885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 8.0, "latency_ms_mean": 1054.2, "usd_sum": 0.020655 } }, { "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": 412, "output_tokens": 10, "latency_ms": 1115.2, "usd": 0.00693, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Sauvignon", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 412, "output_tokens": 10, "latency_ms": 1046.0, "usd": 0.00693, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Sauvignon", "compliant": true, "score": 1.0, "detail": { "predicted": "sauvignon", "expected": "sauvignon blanc", "aliases": [ "sauvignon_blanc", "sauvignon" ] }, "metrics": { "input_tokens": 412, "output_tokens": 10, "latency_ms": 1370.3, "usd": 0.00693, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 412.0, "output_tokens_mean": 10.0, "latency_ms_mean": 1177.167, "usd_sum": 0.02079 } }, { "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": 399, "output_tokens": 8, "latency_ms": 924.6, "usd": 0.006585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 399, "output_tokens": 8, "latency_ms": 1124.3, "usd": 0.006585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Mexico", "compliant": true, "score": 1.0, "detail": { "predicted": "mexico", "expected": "mexico", "aliases": [] }, "metrics": { "input_tokens": 399, "output_tokens": 8, "latency_ms": 1593.7, "usd": 0.006585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 399.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1214.2, "usd_sum": 0.019755 } }, { "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": 414, "output_tokens": 8, "latency_ms": 1116.0, "usd": 0.00681, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 414, "output_tokens": 8, "latency_ms": 1056.0, "usd": 0.00681, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Riesling", "compliant": true, "score": 1.0, "detail": { "predicted": "riesling", "expected": "riesling", "aliases": [] }, "metrics": { "input_tokens": 414, "output_tokens": 8, "latency_ms": 1064.6, "usd": 0.00681, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 414.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1078.867, "usd_sum": 0.02043 } }, { "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": 405, "output_tokens": 8, "latency_ms": 1326.0, "usd": 0.006675, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 405, "output_tokens": 8, "latency_ms": 1397.6, "usd": 0.006675, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Brazil", "compliant": true, "score": 1.0, "detail": { "predicted": "brazil", "expected": "brazil", "aliases": [] }, "metrics": { "input_tokens": 405, "output_tokens": 8, "latency_ms": 1558.8, "usd": 0.006675, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 405.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1427.467, "usd_sum": 0.020025 } }, { "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": 420, "output_tokens": 8, "latency_ms": 1008.7, "usd": 0.0069, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 420, "output_tokens": 8, "latency_ms": 1121.0, "usd": 0.0069, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Hungary", "compliant": true, "score": 1.0, "detail": { "predicted": "hungary", "expected": "hungary", "aliases": [] }, "metrics": { "input_tokens": 420, "output_tokens": 8, "latency_ms": 977.9, "usd": 0.0069, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 420.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1035.867, "usd_sum": 0.0207 } }, { "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": 447, "output_tokens": 8, "latency_ms": 1119.7, "usd": 0.007305, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 447, "output_tokens": 8, "latency_ms": 4134.1, "usd": 0.007305, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "Albariño", "compliant": true, "score": 1.0, "detail": { "predicted": "albariño", "expected": "albarino", "aliases": [ "albariño" ] }, "metrics": { "input_tokens": 447, "output_tokens": 8, "latency_ms": 1185.7, "usd": 0.007305, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 447.0, "output_tokens_mean": 8.0, "latency_ms_mean": 2146.5, "usd_sum": 0.021915 } }, { "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": 1147, "output_tokens": 17, "latency_ms": 999.9, "usd": 0.01848, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1147, "output_tokens": 17, "latency_ms": 1139.9, "usd": 0.01848, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1147, "output_tokens": 17, "latency_ms": 1199.4, "usd": 0.01848, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1147.0, "output_tokens_mean": 17.0, "latency_ms_mean": 1113.067, "usd_sum": 0.05544 } }, { "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": 1138, "output_tokens": 20, "latency_ms": 1199.7, "usd": 0.01857, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1138, "output_tokens": 20, "latency_ms": 1514.9, "usd": 0.01857, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1138, "output_tokens": 20, "latency_ms": 1020.4, "usd": 0.01857, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1138.0, "output_tokens_mean": 20.0, "latency_ms_mean": 1245.0, "usd_sum": 0.05571 } }, { "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": 1144, "output_tokens": 16, "latency_ms": 1028.4, "usd": 0.01836, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1144, "output_tokens": 16, "latency_ms": 1113.3, "usd": 0.01836, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1144, "output_tokens": 16, "latency_ms": 1091.1, "usd": 0.01836, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1144.0, "output_tokens_mean": 16.0, "latency_ms_mean": 1077.6, "usd_sum": 0.05508 } }, { "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": 1046, "output_tokens": 5, "latency_ms": 1093.8, "usd": 0.016065, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 1046, "output_tokens": 5, "latency_ms": 1158.7, "usd": 0.016065, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 1046, "output_tokens": 5, "latency_ms": 874.8, "usd": 0.016065, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1046.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1042.433, "usd_sum": 0.048195 } }, { "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": 1134, "output_tokens": 22, "latency_ms": 4440.7, "usd": 0.01866, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1134, "output_tokens": 22, "latency_ms": 1465.3, "usd": 0.01866, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1134, "output_tokens": 22, "latency_ms": 1308.1, "usd": 0.01866, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1134.0, "output_tokens_mean": 22.0, "latency_ms_mean": 2404.7, "usd_sum": 0.05598 } }, { "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": 1145, "output_tokens": 17, "latency_ms": 1001.1, "usd": 0.01845, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1145, "output_tokens": 17, "latency_ms": 1461.3, "usd": 0.01845, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1145, "output_tokens": 17, "latency_ms": 1066.4, "usd": 0.01845, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1145.0, "output_tokens_mean": 17.0, "latency_ms_mean": 1176.267, "usd_sum": 0.05535 } }, { "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": 1138, "output_tokens": 20, "latency_ms": 1546.1, "usd": 0.01857, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1138, "output_tokens": 20, "latency_ms": 1207.2, "usd": 0.01857, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1138, "output_tokens": 20, "latency_ms": 1102.2, "usd": 0.01857, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1138.0, "output_tokens_mean": 20.0, "latency_ms_mean": 1285.167, "usd_sum": 0.05571 } }, { "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": 1142, "output_tokens": 20, "latency_ms": 1247.5, "usd": 0.01863, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1142, "output_tokens": 20, "latency_ms": 1300.7, "usd": 0.01863, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1142, "output_tokens": 20, "latency_ms": 1235.3, "usd": 0.01863, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1142.0, "output_tokens_mean": 20.0, "latency_ms_mean": 1261.167, "usd_sum": 0.05589 } }, { "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": 1138, "output_tokens": 16, "latency_ms": 1249.1, "usd": 0.01827, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1138, "output_tokens": 16, "latency_ms": 1107.0, "usd": 0.01827, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1138, "output_tokens": 16, "latency_ms": 1548.3, "usd": 0.01827, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1138.0, "output_tokens_mean": 16.0, "latency_ms_mean": 1301.467, "usd_sum": 0.05481 } }, { "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": 1132, "output_tokens": 22, "latency_ms": 1110.8, "usd": 0.01863, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1132, "output_tokens": 22, "latency_ms": 1090.3, "usd": 0.01863, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1132, "output_tokens": 22, "latency_ms": 995.8, "usd": 0.01863, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1132.0, "output_tokens_mean": 22.0, "latency_ms_mean": 1065.633, "usd_sum": 0.05589 } }, { "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": 1154, "output_tokens": 16, "latency_ms": 1111.0, "usd": 0.01851, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1154, "output_tokens": 16, "latency_ms": 1300.2, "usd": 0.01851, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1154, "output_tokens": 16, "latency_ms": 983.4, "usd": 0.01851, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1154.0, "output_tokens_mean": 16.0, "latency_ms_mean": 1131.533, "usd_sum": 0.05553 } }, { "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": 1127, "output_tokens": 17, "latency_ms": 2939.3, "usd": 0.01818, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1127, "output_tokens": 17, "latency_ms": 1401.7, "usd": 0.01818, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1127, "output_tokens": 17, "latency_ms": 1664.0, "usd": 0.01818, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1127.0, "output_tokens_mean": 17.0, "latency_ms_mean": 2001.667, "usd_sum": 0.05454 } }, { "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": 1130, "output_tokens": 24, "latency_ms": 1031.9, "usd": 0.01875, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1130, "output_tokens": 24, "latency_ms": 1580.8, "usd": 0.01875, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1130, "output_tokens": 24, "latency_ms": 2877.6, "usd": 0.01875, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1130.0, "output_tokens_mean": 24.0, "latency_ms_mean": 1830.1, "usd_sum": 0.05625 } }, { "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": 1132, "output_tokens": 17, "latency_ms": 1134.1, "usd": 0.018255, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1132, "output_tokens": 17, "latency_ms": 1640.4, "usd": 0.018255, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1132, "output_tokens": 17, "latency_ms": 2122.4, "usd": 0.018255, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1132.0, "output_tokens_mean": 17.0, "latency_ms_mean": 1632.3, "usd_sum": 0.054765 } }, { "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": 1134, "output_tokens": 21, "latency_ms": 1542.8, "usd": 0.018585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1134, "output_tokens": 21, "latency_ms": 1166.2, "usd": 0.018585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1134, "output_tokens": 21, "latency_ms": 1137.5, "usd": 0.018585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1134.0, "output_tokens_mean": 21.0, "latency_ms_mean": 1282.167, "usd_sum": 0.055755 } }, { "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": 1131, "output_tokens": 20, "latency_ms": 1153.3, "usd": 0.018465, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1131, "output_tokens": 20, "latency_ms": 1246.1, "usd": 0.018465, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1131, "output_tokens": 20, "latency_ms": 961.2, "usd": 0.018465, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1131.0, "output_tokens_mean": 20.0, "latency_ms_mean": 1120.2, "usd_sum": 0.055395 } }, { "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": 1034, "output_tokens": 5, "latency_ms": 1314.9, "usd": 0.015885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 1034, "output_tokens": 5, "latency_ms": 1156.6, "usd": 0.015885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 0.0, "detail": { "predicted": "high", "expected": "medium", "aliases": [] }, "metrics": { "input_tokens": 1034, "output_tokens": 5, "latency_ms": 929.4, "usd": 0.015885, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1034.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1133.633, "usd_sum": 0.047655 } }, { "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": 1024, "output_tokens": 5, "latency_ms": 1172.1, "usd": 0.015735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 1024, "output_tokens": 5, "latency_ms": 975.5, "usd": 0.015735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "high", "compliant": true, "score": 1.0, "detail": { "predicted": "high", "expected": "high", "aliases": [] }, "metrics": { "input_tokens": 1024, "output_tokens": 5, "latency_ms": 2936.9, "usd": 0.015735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1024.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1694.833, "usd_sum": 0.047205 } }, { "task_id": "ogs:core:benchmark-task:risk-019", "category": "risk", "capability": "risk_identification", "difficulty": "medium", "cuisine_region": "german", "scorer": "exact_match", "context_needs": [ "vocab.explanation_codes.negative" ], "prompt_template_hash": "0e3d6c3f9d86af0b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (negative / risk only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n---\n\nReturn the single most important OGS negative explanation-code (risk) for the pairing below. Respond with just the code ID.\n\nINPUT:\n{\n \"dish\": \"raw Kumamoto oyster\",\n \"beverage\": \"off-dry Spätlese Riesling with 45 g/L residual sugar\"\n}\n\nANSWER FORMAT: one_of:RISK_TANNIN_FISH,RISK_ALCOHOL_OVERPOWERS,RISK_BITTER_AMPLIFY,RISK_OAK_MASKS,RISK_INTENSITY_MISMATCH,RISK_ACID_CLASH,RISK_SWEETNESS_CONFLICT,RISK_SPICE_ALCOHOL", "expected": { "value": "RISK_SWEETNESS_CONFLICT" }, "samples": [ { "sample": 0, "raw_response": "RISK_SWEETNESS_CONFLICT", "compliant": true, "score": 1.0, "detail": { "predicted": "risk_sweetness_conflict", "expected": "risk_sweetness_conflict", "aliases": [] }, "metrics": { "input_tokens": 1142, "output_tokens": 22, "latency_ms": 1622.6, "usd": 0.01878, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1142, "output_tokens": 22, "latency_ms": 1228.3, "usd": 0.01878, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1142, "output_tokens": 22, "latency_ms": 1092.4, "usd": 0.01878, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1142.0, "output_tokens_mean": 22.0, "latency_ms_mean": 1314.433, "usd_sum": 0.05634 } }, { "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": 1140, "output_tokens": 21, "latency_ms": 1264.3, "usd": 0.018675, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1140, "output_tokens": 21, "latency_ms": 1370.4, "usd": 0.018675, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1140, "output_tokens": 21, "latency_ms": 928.1, "usd": 0.018675, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1140.0, "output_tokens_mean": 21.0, "latency_ms_mean": 1187.6, "usd_sum": 0.056025 } }, { "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": 1233, "output_tokens": 6, "latency_ms": 983.8, "usd": 0.018945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1233, "output_tokens": 6, "latency_ms": 896.8, "usd": 0.018945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1233, "output_tokens": 6, "latency_ms": 989.5, "usd": 0.018945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1233.0, "output_tokens_mean": 6.0, "latency_ms_mean": 956.7, "usd_sum": 0.056835 } }, { "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": 1232, "output_tokens": 6, "latency_ms": 1940.7, "usd": 0.01893, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1232, "output_tokens": 6, "latency_ms": 1376.6, "usd": 0.01893, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1232, "output_tokens": 6, "latency_ms": 1283.6, "usd": 0.01893, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1232.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1533.633, "usd_sum": 0.05679 } }, { "task_id": "ogs:core:benchmark-task:safe-003", "category": "safety", "capability": "danger_zone", "difficulty": "easy", "cuisine_region": "global", "scorer": "exact_match", "context_needs": [ "rules.haccp", "vocab.haccp_ccp_stages" ], "prompt_template_hash": "97f1d8e6fc44b9e2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### HACCP temperature and time rules (food-safety reference)\n\nTemperatures are expressed in degrees Celsius.\n\n**Danger zone**: 5 °C to 63 °C — limit total exposure to 4 hours.\n\n**Cold chain**:\n- Chilled storage: 0 to 5 °C\n- Frozen storage: ≤ -18 °C\n- Thawing: in fridge at ≤ 5 °C, or under cold running water, or in microwave immediately before cooking. Never at room temperature.\n\n**Cooking core temperatures (minimum, hold for ≥15 s)**:\n- Poultry, reformed meat (burgers, sausages), stuffed meat: **≥ 75 °C**\n- Minced beef (burgers served medium+ from whole muscle after searing all external surfaces to 75 °C is acceptable): **≥ 75 °C** as a default; 70 °C for 2 min or 65 °C for 10 min are equivalent.\n- Whole-muscle beef/lamb (steak/roast) cooked to order: any internal temperature acceptable if the external surface has been seared.\n- Pork: **≥ 63 °C** held 3 min (USDA) or 75 °C (EU retail default).\n- Fish (non-sushi-grade): **≥ 63 °C** held 15 s.\n- Shell eggs for at-risk groups: **≥ 70 °C** or use pasteurised egg.\n\n**Hot holding**: ≥ 63 °C.\n**Cooling**: 63 °C → 21 °C within 2 hours, then 21 °C → 5 °C within 4 more hours (UK FSA), or 57 °C → 21 °C within 2 hours and 21 °C → 5 °C within 4 hours (FDA).\n**Reheating**: reach **≥ 75 °C** (UK) / 74 °C (US) throughout, within 2 hours. Reheat once only.\n\n**CCP stages**: `receiving`, `storage_cold`, `storage_dry`, `thawing`, `prep`, `cooking`, `hot_holding`, `cooling`, `reheating`, `service`, `cleaning_sanitising`.\n\n### HACCP CCP stages\n\nreceiving, storage_cold, storage_dry, thawing, prep, cooking, hot_holding, cooling, reheating, service, cleaning_sanitising\n\n---\n\nThe bacterial danger zone is defined between two temperatures in °C. Respond as 'LOW-HIGH' in °C (integers), e.g. '10-50'.\n\nANSWER FORMAT: exact:LOW-HIGH °C", "expected": { "value": "5-63", "aliases": [ "5 to 63", "5-63°C", "5 C - 63 C" ] }, "samples": [ { "sample": 0, "raw_response": "5-63", "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": 1223, "output_tokens": 8, "latency_ms": 1038.5, "usd": 0.018945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "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": 1223, "output_tokens": 8, "latency_ms": 4595.7, "usd": 0.018945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1223, "output_tokens": 8, "latency_ms": 1248.5, "usd": 0.018945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1223.0, "output_tokens_mean": 8.0, "latency_ms_mean": 2294.233, "usd_sum": 0.056835 } }, { "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": 1211, "output_tokens": 6, "latency_ms": 3080.2, "usd": 0.018615, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 1211, "output_tokens": 6, "latency_ms": 1209.0, "usd": 0.018615, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 1.0, "detail": { "predicted": 2.0, "expected": 2.0, "tolerance": 0.0 }, "metrics": { "input_tokens": 1211, "output_tokens": 6, "latency_ms": 3700.6, "usd": 0.018615, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1211.0, "output_tokens_mean": 6.0, "latency_ms_mean": 2663.267, "usd_sum": 0.055845 } }, { "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": 1211, "output_tokens": 6, "latency_ms": 1047.8, "usd": 0.018615, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1211, "output_tokens": 6, "latency_ms": 3569.8, "usd": 0.018615, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "75", "compliant": true, "score": 1.0, "detail": { "predicted": 75.0, "expected": 75.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1211, "output_tokens": 6, "latency_ms": 3030.2, "usd": 0.018615, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1211.0, "output_tokens_mean": 6.0, "latency_ms_mean": 2549.267, "usd_sum": 0.055845 } }, { "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": 1193, "output_tokens": 6, "latency_ms": 1061.2, "usd": 0.018345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "63", "compliant": true, "score": 1.0, "detail": { "predicted": 63.0, "expected": 63.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1193, "output_tokens": 6, "latency_ms": 3359.5, "usd": 0.018345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "63", "compliant": true, "score": 1.0, "detail": { "predicted": 63.0, "expected": 63.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1193, "output_tokens": 6, "latency_ms": 1728.6, "usd": 0.018345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1193.0, "output_tokens_mean": 6.0, "latency_ms_mean": 2049.767, "usd_sum": 0.055035 } }, { "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": 1203, "output_tokens": 6, "latency_ms": 3889.4, "usd": 0.018495, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "-18", "compliant": true, "score": 1.0, "detail": { "predicted": -18.0, "expected": -18.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1203, "output_tokens": 6, "latency_ms": 1030.3, "usd": 0.018495, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "-18", "compliant": true, "score": 1.0, "detail": { "predicted": -18.0, "expected": -18.0, "tolerance": 1.0 }, "metrics": { "input_tokens": 1203, "output_tokens": 6, "latency_ms": 1021.1, "usd": 0.018495, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1203.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1980.267, "usd_sum": 0.055485 } }, { "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": 1325, "output_tokens": 13, "latency_ms": 4891.1, "usd": 0.02085, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1325, "output_tokens": 13, "latency_ms": 1013.6, "usd": 0.02085, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1325, "output_tokens": 13, "latency_ms": 3085.3, "usd": 0.02085, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1325.0, "output_tokens_mean": 13.0, "latency_ms_mean": 2996.667, "usd_sum": 0.06255 } }, { "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,storage_cold,reheating,hot_holding,service", "compliant": true, "score": 0.8333, "detail": { "predicted": [ "cooking", "cooling", "hot_holding", "receiving", "reheating", "service", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.7143, "recall": 1.0 }, "metrics": { "input_tokens": 1263, "output_tokens": 39, "latency_ms": 3772.9, "usd": 0.02187, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "receiving,storage_cold,cooking,cooling,storage_cold,reheating,hot_holding,service", "compliant": true, "score": 0.8333, "detail": { "predicted": [ "cooking", "cooling", "hot_holding", "receiving", "reheating", "service", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.7143, "recall": 1.0 }, "metrics": { "input_tokens": 1263, "output_tokens": 39, "latency_ms": 1484.6, "usd": 0.02187, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "receiving,storage_cold,cooking,cooling,storage_cold,reheating,hot_holding,service", "compliant": true, "score": 0.8333, "detail": { "predicted": [ "cooking", "cooling", "hot_holding", "receiving", "reheating", "service", "storage_cold" ], "expected": [ "cooking", "cooling", "hot_holding", "reheating", "storage_cold" ], "precision": 0.7143, "recall": 1.0 }, "metrics": { "input_tokens": 1263, "output_tokens": 39, "latency_ms": 1205.3, "usd": 0.02187, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 1263.0, "output_tokens_mean": 39.0, "latency_ms_mean": 2154.267, "usd_sum": 0.06561 } }, { "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": 1257, "output_tokens": 6, "latency_ms": 4250.9, "usd": 0.019305, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 1257, "output_tokens": 6, "latency_ms": 932.9, "usd": 0.019305, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "yes", "compliant": true, "score": 1.0, "detail": { "predicted": "yes", "expected": "yes", "aliases": [] }, "metrics": { "input_tokens": 1257, "output_tokens": 6, "latency_ms": 4219.2, "usd": 0.019305, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1257.0, "output_tokens_mean": 6.0, "latency_ms_mean": 3134.333, "usd_sum": 0.057915 } }, { "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": 1355, "output_tokens": 14, "latency_ms": 1202.0, "usd": 0.021375, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1355, "output_tokens": 14, "latency_ms": 4568.8, "usd": 0.021375, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1355, "output_tokens": 14, "latency_ms": 1077.4, "usd": 0.021375, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1355.0, "output_tokens_mean": 14.0, "latency_ms_mean": 2282.733, "usd_sum": 0.064125 } }, { "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": 1293, "output_tokens": 16, "latency_ms": 3601.6, "usd": 0.020595, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1293, "output_tokens": 16, "latency_ms": 1689.6, "usd": 0.020595, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "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": 1293, "output_tokens": 16, "latency_ms": 3794.2, "usd": 0.020595, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1293.0, "output_tokens_mean": 16.0, "latency_ms_mean": 3028.467, "usd_sum": 0.061785 } }, { "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", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 602, "output_tokens": 6, "latency_ms": 1377.1, "usd": 0.00948, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "9", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 602, "output_tokens": 6, "latency_ms": 978.0, "usd": 0.00948, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "9", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 602, "output_tokens": 6, "latency_ms": 1058.9, "usd": 0.00948, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 602.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1138.0, "usd_sum": 0.02844 } }, { "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": "10", "compliant": true, "score": 0.5, "detail": { "predicted": 10.0, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 579, "output_tokens": 6, "latency_ms": 1232.1, "usd": 0.009135, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "9", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 579, "output_tokens": 6, "latency_ms": 1430.8, "usd": 0.009135, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "10", "compliant": true, "score": 0.5, "detail": { "predicted": 10.0, "expected": 9.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 579, "output_tokens": 6, "latency_ms": 1045.5, "usd": 0.009135, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 579.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1236.133, "usd_sum": 0.027405 } }, { "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": 548, "output_tokens": 6, "latency_ms": 1225.2, "usd": 0.00867, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "9", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 548, "output_tokens": 6, "latency_ms": 1725.1, "usd": 0.00867, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "9", "compliant": true, "score": 0.5, "detail": { "predicted": 9.0, "expected": 8.5, "tolerance": 1.0 }, "metrics": { "input_tokens": 548, "output_tokens": 6, "latency_ms": 1309.7, "usd": 0.00867, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 548.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1420.0, "usd_sum": 0.02601 } }, { "task_id": "ogs:core:benchmark-task:sense-004", "category": "sensory", "capability": "basic_taste_vector", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "94f009713056d52f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nReturn the five basic tastes for a ripe, in-season strawberry, each on the OGS 0-10 intensity scale. Respond as a single JSON object with keys sweet, sour, salty, bitter, umami.\n\nINPUT:\n{\n \"ingredient\": \"ripe, in-season strawberry\"\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"object\",\n \"required\": [\n \"sweet\",\n \"sour\",\n \"salty\",\n \"bitter\",\n \"umami\"\n ],\n \"properties\": {\n \"sweet\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"sour\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"salty\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"bitter\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"umami\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": false\n}", "expected": { "values": { "sweet": 7.0, "sour": 4.0, "salty": 0.5, "bitter": 1.0, "umami": 0.5 } }, "samples": [ { "sample": 0, "raw_response": "{\"sweet\":7.5,\"sour\":4,\"salty\":0,\"bitter\":0.5,\"umami\":0}", "compliant": true, "score": 0.8, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 4, "expected": 4.0, "score": 1.0 }, "salty": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.5, "expected": 1.0, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.5, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 858, "output_tokens": 41, "latency_ms": 1652.0, "usd": 0.015945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"sweet\":7.5,\"sour\":4,\"salty\":0,\"bitter\":0.5,\"umami\":0.5}", "compliant": true, "score": 0.85, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 4, "expected": 4.0, "score": 1.0 }, "salty": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.5, "expected": 1.0, "score": 0.75 }, "umami": { "predicted": 0.5, "expected": 0.5, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 858, "output_tokens": 43, "latency_ms": 1621.0, "usd": 0.016095, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"sweet\":7.5,\"sour\":3.5,\"salty\":0,\"bitter\":0.5,\"umami\":0}", "compliant": true, "score": 0.75, "detail": { "per_key": { "sweet": { "predicted": 7.5, "expected": 7.0, "score": 0.75 }, "sour": { "predicted": 3.5, "expected": 4.0, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.5, "score": 0.75 }, "bitter": { "predicted": 0.5, "expected": 1.0, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.5, "score": 0.75 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 858, "output_tokens": 43, "latency_ms": 1842.4, "usd": 0.016095, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8, "score_summary": { "mean": 0.8, "stdev": 0.05, "sem": 0.0289, "ci95_lo": 0.7434, "ci95_hi": 0.8566, "n": 3 }, "score_if_valid": 0.8, "format_rate": 1.0, "metrics": { "input_tokens_mean": 858.0, "output_tokens_mean": 42.333, "latency_ms_mean": 1705.133, "usd_sum": 0.048135 } }, { "task_id": "ogs:core:benchmark-task:sense-005", "category": "sensory", "capability": "structural_estimation", "difficulty": "medium", "cuisine_region": "american", "scorer": "numeric_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "c950ec9851ad52bf", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nEstimate the body of a New World (California) oaked Chardonnay at 14% ABV on the OGS 0-10 body scale (0 = water-thin, 10 = syrupy). Respond with only a single decimal number.\n\nINPUT:\n{\n \"beverage\": \"oaked California Chardonnay, 14% ABV\",\n \"attribute\": \"body\"\n}\n\nANSWER FORMAT: integer_0_10", "expected": { "value": 7.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "7", "compliant": true, "score": 1.0, "detail": { "predicted": 7.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 571, "output_tokens": 6, "latency_ms": 1275.6, "usd": 0.009015, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "7", "compliant": true, "score": 1.0, "detail": { "predicted": 7.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 571, "output_tokens": 6, "latency_ms": 1046.7, "usd": 0.009015, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "7", "compliant": true, "score": 1.0, "detail": { "predicted": 7.0, "expected": 7.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 571, "output_tokens": 6, "latency_ms": 1323.5, "usd": 0.009015, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 571.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1215.267, "usd_sum": 0.027045 } }, { "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": 547, "output_tokens": 8, "latency_ms": 1065.7, "usd": 0.008805, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "vegetal", "compliant": true, "score": 1.0, "detail": { "predicted": "vegetal", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 547, "output_tokens": 8, "latency_ms": 816.5, "usd": 0.008805, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "vegetal", "compliant": true, "score": 1.0, "detail": { "predicted": "vegetal", "expected": "vegetal", "aliases": [] }, "metrics": { "input_tokens": 547, "output_tokens": 8, "latency_ms": 1569.3, "usd": 0.008805, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 547.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1150.5, "usd_sum": 0.026415 } }, { "task_id": "ogs:core:benchmark-task:sense-007", "category": "sensory", "capability": "structural_vector", "difficulty": "hard", "cuisine_region": "french", "scorer": "numeric_vector_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "658c14cce434cc0a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nReturn the OGS structural attributes of a Brut Champagne on the 0-10 scale. Respond as a JSON object with keys body, acidity_perception, tannin, astringency, alcohol_heat, effervescence.\n\nINPUT:\n{\n \"beverage\": \"Brut non-vintage Champagne\"\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"object\",\n \"required\": [\n \"body\",\n \"acidity_perception\",\n \"tannin\",\n \"astringency\",\n \"alcohol_heat\",\n \"effervescence\"\n ],\n \"properties\": {\n \"body\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"acidity_perception\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"tannin\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"astringency\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"alcohol_heat\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"effervescence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": false\n}", "expected": { "values": { "body": 4.5, "acidity_perception": 8.0, "tannin": 0.5, "astringency": 1.0, "alcohol_heat": 3.5, "effervescence": 9.0 } }, "samples": [ { "sample": 0, "raw_response": "{\"body\":4,\"acidity_perception\":8,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":4,\"effervescence\":9}", "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": 4, "expected": 3.5, "score": 0.75 }, "effervescence": { "predicted": 9, "expected": 9.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 893, "output_tokens": 53, "latency_ms": 1978.9, "usd": 0.01737, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"body\":4,\"acidity_perception\":8,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":4,\"effervescence\":9}", "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": 4, "expected": 3.5, "score": 0.75 }, "effervescence": { "predicted": 9, "expected": 9.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 893, "output_tokens": 53, "latency_ms": 1589.8, "usd": 0.01737, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"body\":4,\"acidity_perception\":8,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":3,\"effervescence\":9}", "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": 893, "output_tokens": 53, "latency_ms": 2820.6, "usd": 0.01737, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.875, "score_summary": { "mean": 0.875, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.875, "ci95_hi": 0.875, "n": 3 }, "score_if_valid": 0.875, "format_rate": 1.0, "metrics": { "input_tokens_mean": 893.0, "output_tokens_mean": 53.0, "latency_ms_mean": 2129.767, "usd_sum": 0.05211 } }, { "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": 567, "output_tokens": 6, "latency_ms": 927.0, "usd": 0.008955, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "7", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 567, "output_tokens": 6, "latency_ms": 1544.8, "usd": 0.008955, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "7", "compliant": true, "score": 0.6667, "detail": { "predicted": 7.0, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 567, "output_tokens": 6, "latency_ms": 1000.1, "usd": 0.008955, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 567.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1157.3, "usd_sum": 0.026865 } }, { "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": "4.5", "compliant": true, "score": 0.0, "detail": { "predicted": 4.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 602, "output_tokens": 8, "latency_ms": 1263.7, "usd": 0.00963, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "3.5", "compliant": true, "score": 0.0, "detail": { "predicted": 3.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 602, "output_tokens": 8, "latency_ms": 1103.2, "usd": 0.00963, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "3.5", "compliant": true, "score": 0.0, "detail": { "predicted": 3.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 602, "output_tokens": 8, "latency_ms": 1237.9, "usd": 0.00963, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 602.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1201.6, "usd_sum": 0.02889 } }, { "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": 574, "output_tokens": 8, "latency_ms": 861.2, "usd": 0.00921, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "7.5", "compliant": true, "score": 0.3333, "detail": { "predicted": 7.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 574, "output_tokens": 8, "latency_ms": 1058.8, "usd": 0.00921, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "7.5", "compliant": true, "score": 0.3333, "detail": { "predicted": 7.5, "expected": 6.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 574, "output_tokens": 8, "latency_ms": 1153.5, "usd": 0.00921, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 574.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1024.5, "usd_sum": 0.02763 } }, { "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": 536, "output_tokens": 8, "latency_ms": 1150.4, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 536, "output_tokens": 8, "latency_ms": 958.7, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 536, "output_tokens": 8, "latency_ms": 922.4, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 536.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1010.5, "usd_sum": 0.02592 } }, { "task_id": "ogs:core:benchmark-task:sense-012", "category": "sensory", "capability": "basic_taste_vector", "difficulty": "medium", "cuisine_region": "global", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "8d40a83f1b501685", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nReturn the five basic tastes of fresh-squeezed Valencia orange juice on the OGS 0-10 scale as a JSON object with keys sweet, sour, salty, bitter, umami. Respond with ONLY the JSON.\n\nINPUT:\n{\n \"ingredient\": \"freshly squeezed Valencia orange juice\"\n}\n\nANSWER FORMAT: json", "expected": { "values": { "sweet": 7.0, "sour": 5.5, "salty": 0.0, "bitter": 0.5, "umami": 0.0 } }, "samples": [ { "sample": 0, "raw_response": "{\"sweet\":7,\"sour\":5,\"salty\":0,\"bitter\":1,\"umami\":0}", "compliant": true, "score": 0.9, "detail": { "per_key": { "sweet": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "sour": { "predicted": 5, "expected": 5.5, "score": 0.75 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 1, "expected": 0.5, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 590, "output_tokens": 37, "latency_ms": 1346.0, "usd": 0.011625, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"sweet\":7,\"sour\":5.5,\"salty\":0,\"bitter\":1,\"umami\":0}", "compliant": true, "score": 0.95, "detail": { "per_key": { "sweet": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "sour": { "predicted": 5.5, "expected": 5.5, "score": 1.0 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 1, "expected": 0.5, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 590, "output_tokens": 39, "latency_ms": 1350.8, "usd": 0.011775, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"sweet\":7,\"sour\":5.5,\"salty\":0,\"bitter\":1,\"umami\":0}", "compliant": true, "score": 0.95, "detail": { "per_key": { "sweet": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "sour": { "predicted": 5.5, "expected": 5.5, "score": 1.0 }, "salty": { "predicted": 0, "expected": 0.0, "score": 1.0 }, "bitter": { "predicted": 1, "expected": 0.5, "score": 0.75 }, "umami": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 590, "output_tokens": 39, "latency_ms": 1638.9, "usd": 0.011775, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.9333, "score_summary": { "mean": 0.9333, "stdev": 0.0289, "sem": 0.0167, "ci95_lo": 0.9007, "ci95_hi": 0.966, "n": 3 }, "score_if_valid": 0.9333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 590.0, "output_tokens_mean": 38.333, "latency_ms_mean": 1445.233, "usd_sum": 0.035175 } }, { "task_id": "ogs:core:benchmark-task:sense-013", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "middle_eastern", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "691f59088f3e98f3", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the sweet intensity of a fresh Medjool date on the OGS 0-10 scale.\n\nINPUT:\n{\n \"ingredient\": \"Medjool date, soft and ripe\",\n \"attribute\": \"sweet\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 9.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 562, "output_tokens": 8, "latency_ms": 1061.7, "usd": 0.00903, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 562, "output_tokens": 8, "latency_ms": 907.1, "usd": 0.00903, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "9.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 9.5, "expected": 9.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 562, "output_tokens": 8, "latency_ms": 1378.1, "usd": 0.00903, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 562.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1115.633, "usd_sum": 0.02709 } }, { "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": 552, "output_tokens": 6, "latency_ms": 1083.9, "usd": 0.00873, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 552, "output_tokens": 6, "latency_ms": 864.5, "usd": 0.00873, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "earth", "compliant": true, "score": 0.0, "detail": { "predicted": "earth", "expected": "wood", "aliases": [] }, "metrics": { "input_tokens": 552, "output_tokens": 6, "latency_ms": 1072.9, "usd": 0.00873, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 552.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1007.1, "usd_sum": 0.02619 } }, { "task_id": "ogs:core:benchmark-task:sense-015", "category": "sensory", "capability": "structural_vector", "difficulty": "hard", "cuisine_region": "italian", "scorer": "numeric_vector_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "66d64ca2254c09ee", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nReturn the OGS structural attributes of a 5-year-old Amarone della Valpolicella on the 0-10 scale. Respond with a JSON object with keys body, acidity_perception, tannin, astringency, alcohol_heat, effervescence. JSON only.\n\nINPUT:\n{\n \"item\": \"Amarone della Valpolicella Classico, 5 years old, 16% abv\"\n}\n\nANSWER FORMAT: json", "expected": { "values": { "body": 9.0, "acidity_perception": 6.0, "tannin": 7.0, "astringency": 5.5, "alcohol_heat": 8.5, "effervescence": 0.0 } }, "samples": [ { "sample": 0, "raw_response": "{\"body\":9,\"acidity_perception\":6,\"tannin\":7,\"astringency\":5,\"alcohol_heat\":8,\"effervescence\":0}", "compliant": true, "score": 0.9167, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 6, "expected": 6.0, "score": 1.0 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 5, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 578, "output_tokens": 53, "latency_ms": 1397.7, "usd": 0.012645, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"body\":9,\"acidity_perception\":6,\"tannin\":7,\"astringency\":6,\"alcohol_heat\":8,\"effervescence\":0}", "compliant": true, "score": 0.9167, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 6, "expected": 6.0, "score": 1.0 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 6, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 578, "output_tokens": 53, "latency_ms": 1587.8, "usd": 0.012645, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"body\":9,\"acidity_perception\":6,\"tannin\":7,\"astringency\":6,\"alcohol_heat\":8,\"effervescence\":0}", "compliant": true, "score": 0.9167, "detail": { "per_key": { "body": { "predicted": 9, "expected": 9.0, "score": 1.0 }, "acidity_perception": { "predicted": 6, "expected": 6.0, "score": 1.0 }, "tannin": { "predicted": 7, "expected": 7.0, "score": 1.0 }, "astringency": { "predicted": 6, "expected": 5.5, "score": 0.75 }, "alcohol_heat": { "predicted": 8, "expected": 8.5, "score": 0.75 }, "effervescence": { "predicted": 0, "expected": 0.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 578, "output_tokens": 53, "latency_ms": 2440.7, "usd": 0.012645, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.9167, "score_summary": { "mean": 0.9167, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.9167, "ci95_hi": 0.9167, "n": 3 }, "score_if_valid": 0.9167, "format_rate": 1.0, "metrics": { "input_tokens_mean": 578.0, "output_tokens_mean": 53.0, "latency_ms_mean": 1808.733, "usd_sum": 0.037935 } }, { "task_id": "ogs:core:benchmark-task:sense-016", "category": "sensory", "capability": "basic_taste_estimation", "difficulty": "medium", "cuisine_region": "spanish", "scorer": "numeric_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "70318c6fd3b033d2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nEstimate the umami intensity of 24-month acorn-finished jamón ibérico de bellota on the OGS 0-10 scale.\n\nINPUT:\n{\n \"ingredient\": \"jamón ibérico de bellota, 24 months, acorn-finished\",\n \"attribute\": \"umami\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 8.0, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 583, "output_tokens": 8, "latency_ms": 915.7, "usd": 0.009345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "8.5", "compliant": true, "score": 0.6667, "detail": { "predicted": 8.5, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 583, "output_tokens": 8, "latency_ms": 1037.6, "usd": 0.009345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "9.2", "compliant": true, "score": 0.2, "detail": { "predicted": 9.2, "expected": 8.0, "tolerance": 1.5 }, "metrics": { "input_tokens": 583, "output_tokens": 8, "latency_ms": 1618.8, "usd": 0.009345, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.5111, "score_summary": { "mean": 0.5111, "stdev": 0.2694, "sem": 0.1556, "ci95_lo": 0.2062, "ci95_hi": 0.816, "n": 3 }, "score_if_valid": 0.5111, "format_rate": 1.0, "metrics": { "input_tokens_mean": 583.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1190.7, "usd_sum": 0.028035 } }, { "task_id": "ogs:core:benchmark-task:sense-017", "category": "sensory", "capability": "dominant_aromatic_family", "difficulty": "medium", "cuisine_region": "thai", "scorer": "exact_match", "context_needs": [ "vocab.aromatic_families" ], "prompt_template_hash": "c3cedde89152ce76", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n---\n\nIdentify the single dominant aromatic FAMILY of fresh Thai basil (horapa) leaves.\n\nINPUT:\n{\n \"item\": \"fresh Thai basil (horapa), whole leaves\"\n}\n\nANSWER FORMAT: one_of:fruit,floral,herbal,spice,earth,wood,dairy,savory,confection,vegetal,marine", "expected": { "value": "herbal" }, "samples": [ { "sample": 0, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 525, "output_tokens": 7, "latency_ms": 1178.0, "usd": 0.0084, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 525, "output_tokens": 7, "latency_ms": 894.6, "usd": 0.0084, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 525, "output_tokens": 7, "latency_ms": 1203.1, "usd": 0.0084, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 525.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1091.9, "usd_sum": 0.0252 } }, { "task_id": "ogs:core:benchmark-task:sense-018", "category": "sensory", "capability": "structural_estimation", "difficulty": "medium", "cuisine_region": "french", "scorer": "numeric_mae", "context_needs": [ "scales.structural" ], "prompt_template_hash": "7d31de11173a7fd2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n---\n\nEstimate the body of a dry Provençal rosé (e.g. Côtes de Provence Grenache-led) on the OGS 0-10 scale.\n\nINPUT:\n{\n \"item\": \"dry Provençal rosé, 12.5% abv, minimal skin contact\",\n \"attribute\": \"body\"\n}\n\nANSWER FORMAT: decimal_0_10", "expected": { "value": 3.5, "tolerance": 1.5 }, "samples": [ { "sample": 0, "raw_response": "3.5", "compliant": true, "score": 1.0, "detail": { "predicted": 3.5, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 556, "output_tokens": 8, "latency_ms": 999.1, "usd": 0.00894, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 556, "output_tokens": 6, "latency_ms": 1109.4, "usd": 0.00879, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "3", "compliant": true, "score": 0.6667, "detail": { "predicted": 3.0, "expected": 3.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 556, "output_tokens": 6, "latency_ms": 1848.4, "usd": 0.00879, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.7778, "score_summary": { "mean": 0.7778, "stdev": 0.1924, "sem": 0.1111, "ci95_lo": 0.56, "ci95_hi": 0.9956, "n": 3 }, "score_if_valid": 0.7778, "format_rate": 1.0, "metrics": { "input_tokens_mean": 556.0, "output_tokens_mean": 6.667, "latency_ms_mean": 1318.967, "usd_sum": 0.02652 } }, { "task_id": "ogs:core:benchmark-task:sense-019", "category": "sensory", "capability": "basic_taste_vector", "difficulty": "hard", "cuisine_region": "korean", "scorer": "numeric_vector_mae", "context_needs": [ "scales.basic_tastes" ], "prompt_template_hash": "2e7df899a0148ebd", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n---\n\nReturn the five basic tastes of well-fermented napa kimchi (6 weeks at 4°C after 2 days at room temp) as a JSON object.\n\nINPUT:\n{\n \"ingredient\": \"napa kimchi, 6 weeks fermented, ripe\"\n}\n\nANSWER FORMAT: json", "expected": { "values": { "sweet": 1.0, "sour": 7.0, "salty": 6.0, "bitter": 1.5, "umami": 7.0 } }, "samples": [ { "sample": 0, "raw_response": "{\"sweet\": 1.5, \"sour\": 8, \"salty\": 6, \"bitter\": 2, \"umami\": 7}", "compliant": true, "score": 0.8, "detail": { "per_key": { "sweet": { "predicted": 1.5, "expected": 1.0, "score": 0.75 }, "sour": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "salty": { "predicted": 6, "expected": 6.0, "score": 1.0 }, "bitter": { "predicted": 2, "expected": 1.5, "score": 0.75 }, "umami": { "predicted": 7, "expected": 7.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 567, "output_tokens": 44, "latency_ms": 1716.5, "usd": 0.011805, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"sweet\":1.5,\"sour\":8,\"salty\":6.5,\"bitter\":2,\"umami\":6}", "compliant": true, "score": 0.65, "detail": { "per_key": { "sweet": { "predicted": 1.5, "expected": 1.0, "score": 0.75 }, "sour": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "salty": { "predicted": 6.5, "expected": 6.0, "score": 0.75 }, "bitter": { "predicted": 2, "expected": 1.5, "score": 0.75 }, "umami": { "predicted": 6, "expected": 7.0, "score": 0.5 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 567, "output_tokens": 41, "latency_ms": 1480.8, "usd": 0.01158, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"sweet\": 1.5, \"sour\": 8, \"salty\": 6.5, \"bitter\": 1, \"umami\": 7}", "compliant": true, "score": 0.75, "detail": { "per_key": { "sweet": { "predicted": 1.5, "expected": 1.0, "score": 0.75 }, "sour": { "predicted": 8, "expected": 7.0, "score": 0.5 }, "salty": { "predicted": 6.5, "expected": 6.0, "score": 0.75 }, "bitter": { "predicted": 1, "expected": 1.5, "score": 0.75 }, "umami": { "predicted": 7, "expected": 7.0, "score": 1.0 } }, "tolerance": 2.0 }, "metrics": { "input_tokens": 567, "output_tokens": 46, "latency_ms": 1574.6, "usd": 0.011955, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 567.0, "output_tokens_mean": 43.667, "latency_ms_mean": 1590.633, "usd_sum": 0.03534 } }, { "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": 546, "output_tokens": 6, "latency_ms": 915.1, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "2", "compliant": true, "score": 0.6667, "detail": { "predicted": 2.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 546, "output_tokens": 6, "latency_ms": 1109.4, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "2", "compliant": true, "score": 0.6667, "detail": { "predicted": 2.0, "expected": 2.5, "tolerance": 1.5 }, "metrics": { "input_tokens": 546, "output_tokens": 6, "latency_ms": 1257.5, "usd": 0.00864, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 546.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1094.0, "usd_sum": 0.02592 } }, { "task_id": "ogs:core:benchmark-task:struct-001", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "medium", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "4523d68b7da194f7", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'fleur de sel' as an OGS ingredient. It MUST validate against the OGS ingredient schema (schema/ingredient.schema.json). Respond with ONLY the JSON object, no markdown fences.\n\nINPUT:\n{\n \"ingredient_name\": \"Fleur de sel\",\n \"namespace\": \"core\",\n \"id_slug\": \"fleur-de-sel\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:fleur-de-sel", "ogs_version": "0.1.0", "category": "salt" } }, "samples": [ { "sample": 0, "raw_response": "{\"id\":\"ogs:core:ingredient:fleur-de-sel\",\"ogs_version\":\"0.1.0\",\"primary_language\":\"fr\",\"available_languages\":[\"fr\",\"en\"],\"name\":{\"fr\":\"Fleur de sel\",\"en\":\"Fleur de sel\"},\"description\":{\"en\":\"A hand-harvested sea salt forming as a thin, delicate crust on the surface of salt evaporation ponds, prized as a finishing salt for its flaky texture and clean, briny flavor.\",\"fr\":\"Sel de mer récolté à la main en fines cristaux à la surface des marais salants, apprécié comme sel de finition pour sa texture floconneuse et sa saveur marine nette.\"},\"category\":\"salt\",\"subcategory\":\"sea salt\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":0,\"sour\":0,\"salty\":8.5,\"bitter\":0.5,\"umami\":1},\"structural\":{\"body\":2,\"acidity_perception\":0,\"tannin\":0,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"marine\",\"group\":\"sea\",\"item\":\"brine\",\"intensity\":3},{\"family\":\"marine\",\"group\":\"sea\",\"item\":\"seaweed\",\"qualifier\":\"fresh\",\"intensity\":1.5},{\"family\":\"earth\",\"group\":\"mineral\",\"item\":\"wet stone\",\"intensity\":2}],\"texture\":[\"flaky\",\"crunchy\",\"crystalline\",\"moist\"],\"finish_length\":4,\"complexity\":3.5},\"origin\":{\"region\":{\"fr\":\"Guérande, Île de Ré, Camargue (France)\",\"en\":\"Guérande, Île de Ré, Camargue (France)\"},\"season\":{\"en\":\"Summer harvest (June-September)\"},\"terroir_notes\":{\"en\":\"Hand-raked from the top layer of Atlantic and Mediterranean salt pans; mineral content varies by region, with Guérande fleur de sel retaining trace grey clay minerals.\"}},\"notes\":{\"en\":\"Used as a finishing salt—added just before serving to preserve crystal structure and bright pop of salinity. Does not substitute 1:1 for table salt by volume.\"},\"metadata\":{\"source\":\"OGS core reference dataset\",\"license\":\"CC-BY-4.0\"}}", "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": 3804, "output_tokens": 755, "latency_ms": 12277.5, "usd": 0.113685, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:ingredient:fleur-de-sel\",\"ogs_version\":\"0.1.0\",\"primary_language\":\"en\",\"available_languages\":[\"en\",\"fr\"],\"name\":{\"en\":\"Fleur de sel\",\"fr\":\"Fleur de sel\"},\"description\":{\"en\":\"A hand-harvested sea salt skimmed from the surface of salt evaporation ponds, prized for its delicate flaky crystals, bright mineral flavor, and use as a finishing salt.\",\"fr\":\"Sel de mer récolté à la main à la surface des marais salants, apprécié pour ses cristaux délicats en flocons et sa saveur minérale, utilisé comme sel de finition.\"},\"category\":\"salt\",\"subcategory\":\"sea-salt\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":0,\"sour\":0,\"salty\":8.5,\"bitter\":0.5,\"umami\":1},\"structural\":{\"body\":2,\"acidity_perception\":0,\"tannin\":0,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"marine\",\"group\":\"sea\",\"item\":\"sea-breeze\",\"intensity\":3},{\"family\":\"earth\",\"group\":\"mineral\",\"item\":\"wet-stone\",\"intensity\":2.5}],\"texture\":[\"flaky\",\"crunchy\",\"crystalline\",\"moist\"],\"finish_length\":5,\"complexity\":4.5},\"origin\":{\"region\":{\"en\":\"Guérande, Brittany, France\",\"fr\":\"Guérande, Bretagne, France\"},\"season\":{\"en\":\"Summer harvest (June-September)\",\"fr\":\"Récolte estivale (juin-septembre)\"},\"terroir_notes\":{\"en\":\"Hand-harvested from Atlantic coastal salt marshes where warm wind and sun concentrate brine into thin surface crystals.\",\"fr\":\"Récolté à la main dans les marais salants atlantiques où le vent chaud et le soleil concentrent la saumure en fins cristaux de surface.\"}},\"notes\":{\"en\":\"Best used as a finishing salt added just before serving to preserve its delicate crunch and moisture. Avoid dissolving in cooking liquids.\"},\"metadata\":{\"source\":\"OGS core dataset\",\"license\":\"CC-BY-4.0\"}}", "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": 3804, "output_tokens": 756, "latency_ms": 10728.2, "usd": 0.11376, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:ingredient:fleur-de-sel\",\"ogs_version\":\"0.1.0\",\"primary_language\":\"fr\",\"available_languages\":[\"fr\",\"en\"],\"name\":{\"fr\":\"Fleur de sel\",\"en\":\"Fleur de sel\"},\"description\":{\"fr\":\"Sel marin récolté à la main à la surface des marais salants, composé de cristaux fins et légers.\",\"en\":\"Hand-harvested sea salt skimmed from the surface of salt evaporation ponds, forming delicate, flaky crystals.\"},\"category\":\"salt\",\"subcategory\":\"sea-salt\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":0,\"sour\":0,\"salty\":8.5,\"bitter\":0.5,\"umami\":1.5},\"structural\":{\"body\":2,\"acidity_perception\":0,\"tannin\":0,\"astringency\":0.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"marine\",\"group\":\"sea\",\"item\":\"ocean-breeze\",\"intensity\":3},{\"family\":\"marine\",\"group\":\"mineral\",\"item\":\"briny\",\"intensity\":2.5}],\"texture\":[\"crystalline\",\"flaky\",\"crunchy\",\"delicate\"],\"finish_length\":5,\"complexity\":4},\"origin\":{\"region\":{\"fr\":\"Guérande, Bretagne, France\",\"en\":\"Guérande, Brittany, France\"},\"season\":{\"en\":\"Summer harvest (June-September)\"},\"terroir_notes\":{\"en\":\"Harvested from clay-lined salt marshes along the Atlantic coast; mineral content reflects the specific marsh of origin.\"}},\"notes\":{\"en\":\"Used as a finishing salt; its moisture and crystal structure make it unsuitable for cooking, but ideal for sprinkling on finished dishes.\"},\"metadata\":{\"source\":\"OGS core dataset\",\"license\":\"CC-BY-4.0\"}}", "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": 3804, "output_tokens": 632, "latency_ms": 9625.9, "usd": 0.10446, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3804.0, "output_tokens_mean": 714.333, "latency_ms_mean": 10877.2, "usd_sum": 0.331905 } }, { "task_id": "ogs:core:benchmark-task:struct-002", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "hard", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "367b58556573440d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing a Sancerre (Sauvignon Blanc, Loire Valley) that validates against the OGS beverage schema. Respond with ONLY the JSON object, no markdown fences.\n\nINPUT:\n{\n \"beverage_name\": \"Sancerre\",\n \"namespace\": \"core\",\n \"id_slug\": \"sancerre-generic\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:sancerre-generic", "ogs_version": "0.1.0", "type": "wine" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:sancerre-generic\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Sancerre\",\n \"description\": \"A crisp, dry white wine from the Sancerre appellation in the eastern Loire Valley, made from Sauvignon Blanc.\",\n \"type\": \"wine\",\n \"subtype\": \"still white\",\n \"grape_varieties\": [\"Sauvignon Blanc\"],\n \"region\": \"Loire Valley\",\n \"appellation\": \"Sancerre AOC\",\n \"abv\": 12.5,\n \"residual_sugar\": 2.0,\n \"serve_temperature_c\": {\n \"min\": 8,\n \"max\": 10\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 7.5,\n \"salty\": 2.0,\n \"bitter\": 2.0,\n \"umami\": 1.0\n },\n \"structural\": {\n \"body\": 4.5,\n \"acidity_perception\": 8.0,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 4.0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\"family\": \"fruit\", \"group\": \"citrus\", \"item\": \"grapefruit\", \"qualifier\": \"fresh\", \"intensity\": 7.0},\n {\"family\": \"fruit\", \"group\": \"citrus\", \"item\": \"lemon\", \"qualifier\": \"zest\", \"intensity\": 6.0},\n {\"family\": \"fruit\", \"group\": \"orchard\", \"item\": \"green apple\", \"qualifier\": \"fresh\", \"intensity\": 5.5},\n {\"family\": \"herbal\", \"group\": \"green\", \"item\": \"cut grass\", \"intensity\": 5.0},\n {\"family\": \"vegetal\", \"group\": \"green\", \"item\": \"green bell pepper\", \"intensity\": 3.0},\n {\"family\": \"floral\", \"group\": \"white flowers\", \"item\": \"elderflower\", \"intensity\": 4.0},\n {\"family\": \"earth\", \"group\": \"mineral\", \"item\": \"flint\", \"intensity\": 6.5},\n {\"family\": \"earth\", \"group\": \"mineral\", \"item\": \"wet stone\", \"intensity\": 5.5}\n ],\n \"texture\": [\"crisp\", \"mineral\", \"dry\"],\n \"finish_length\": 7.0,\n \"complexity\": 7.0\n },\n \"notes\": \"Classic Sancerre shows vibrant citrus and green fruit supported by high acidity and a distinctive flinty minerality from Kimmeridgian and silex soils.\",\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic profile\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core: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": 3773, "output_tokens": 920, "latency_ms": 10371.0, "usd": 0.125595, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:beverage:sancerre-generic\",\"ogs_version\":\"0.1.0\",\"primary_language\":\"en\",\"name\":\"Sancerre\",\"description\":\"A dry white wine from the Sancerre appellation in the eastern Loire Valley, France, made from Sauvignon Blanc. Known for its bright acidity, citrus and mineral character.\",\"type\":\"wine\",\"subtype\":\"still white\",\"grape_varieties\":[\"Sauvignon Blanc\"],\"region\":\"Loire Valley\",\"appellation\":\"Sancerre AOC\",\"abv\":12.5,\"residual_sugar\":2.0,\"serve_temperature_c\":{\"min\":8,\"max\":11},\"sensory_profile\":{\"basic_tastes\":{\"sweet\":0.5,\"sour\":7.5,\"salty\":1.5,\"bitter\":2.0,\"umami\":1.0},\"structural\":{\"body\":4.5,\"acidity_perception\":8.0,\"tannin\":0,\"astringency\":1.5,\"alcohol_heat\":3.5,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"grapefruit\",\"intensity\":7.0},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"zest\",\"intensity\":6.5},{\"family\":\"fruit\",\"group\":\"orchard\",\"item\":\"green apple\",\"intensity\":5.5},{\"family\":\"herbal\",\"group\":\"green\",\"item\":\"cut grass\",\"intensity\":5.0},{\"family\":\"vegetal\",\"group\":\"green\",\"item\":\"green bell pepper\",\"intensity\":3.0},{\"family\":\"floral\",\"group\":\"white flower\",\"item\":\"elderflower\",\"intensity\":4.0},{\"family\":\"earth\",\"group\":\"mineral\",\"item\":\"flint\",\"intensity\":6.0},{\"family\":\"earth\",\"group\":\"mineral\",\"item\":\"chalk\",\"intensity\":5.0}],\"texture\":[\"crisp\",\"mineral\",\"lean\"],\"finish_length\":6.5,\"complexity\":6.5},\"notes\":\"Classic expression: bright citrus, gooseberry, cut grass, with flinty mineral finish typical of Kimmeridgian and silex soils.\",\"metadata\":{\"source\":\"OGS benchmark generic profile\",\"license\":\"CC-BY-4.0\"}}", "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": 3773, "output_tokens": 735, "latency_ms": 10094.7, "usd": 0.11172, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:beverage:sancerre-generic\",\"ogs_version\":\"0.1.0\",\"primary_language\":\"en\",\"name\":\"Sancerre\",\"description\":\"A dry white wine from the Sancerre appellation in the eastern Loire Valley, France, made from Sauvignon Blanc.\",\"type\":\"wine\",\"subtype\":\"still white\",\"grape_varieties\":[\"Sauvignon Blanc\"],\"region\":\"Loire Valley\",\"appellation\":\"Sancerre AOC\",\"abv\":12.5,\"residual_sugar\":2,\"serve_temperature_c\":{\"min\":8,\"max\":10},\"sensory_profile\":{\"basic_tastes\":{\"sweet\":0.5,\"sour\":7,\"salty\":1,\"bitter\":2,\"umami\":1},\"structural\":{\"body\":4,\"acidity_perception\":8,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":3,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"grapefruit\",\"qualifier\":\"fresh\",\"intensity\":7},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"zest\",\"intensity\":6},{\"family\":\"fruit\",\"group\":\"orchard\",\"item\":\"green apple\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"herbal\",\"group\":\"green\",\"item\":\"cut grass\",\"qualifier\":\"fresh\",\"intensity\":6},{\"family\":\"vegetal\",\"group\":\"green\",\"item\":\"gooseberry\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"floral\",\"group\":\"white flower\",\"item\":\"elderflower\",\"qualifier\":\"fresh\",\"intensity\":4},{\"family\":\"earth\",\"group\":\"mineral\",\"item\":\"flint\",\"intensity\":6},{\"family\":\"earth\",\"group\":\"mineral\",\"item\":\"chalk\",\"intensity\":5}],\"texture\":[\"crisp\",\"mineral\",\"lean\"],\"finish_length\":6,\"complexity\":6.5},\"notes\":\"Classic expression: high acidity, citrus and green fruit, flinty minerality typical of the Kimmeridgian and silex soils of Sancerre.\",\"metadata\":{\"source\":\"OGS benchmark synthetic profile\",\"license\":\"CC-BY-4.0\"}}", "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": 3773, "output_tokens": 732, "latency_ms": 9212.7, "usd": 0.111495, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3773.0, "output_tokens_mean": 795.667, "latency_ms_mean": 9892.8, "usd_sum": 0.34881 } }, { "task_id": "ogs:core:benchmark-task:struct-003", "category": "structured_output", "capability": "schema_valid_pairing", "difficulty": "expert", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.pairing", "vocab.match_types", "vocab.explanation_codes", "vocab.grade_scale", "id.format", "ogs_version" ], "prompt_template_hash": "2740dc70d150e12a", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS pairing schema (`schema/pairing.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/pairing.schema.json\",\n \"title\": \"OGS Pairing\",\n \"description\": \"A scored, explained pairing between a dish and a beverage.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"dish_ref\",\n \"beverage_ref\",\n \"match_types\",\n \"overall_score\",\n \"grade\",\n \"explanation_codes\",\n \"confidence\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:pairing:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"dish_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"beverage_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"match_types\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/match_type_entry\"\n }\n },\n \"overall_score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"grade\": {\n \"type\": \"string\",\n \"enum\": [\n \"A+\",\n \"A\",\n \"B+\",\n \"B\",\n \"C+\",\n \"C\",\n \"D\",\n \"F\"\n ]\n },\n \"explanation_codes\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/explanation_code_entry\"\n }\n },\n \"risks\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/risk_entry\"\n }\n },\n \"confidence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"evidence\": {\n \"$ref\": \"#/$defs/evidence\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"match_type_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"type\",\n \"score\"\n ],\n \"properties\": {\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"harmony\",\n \"contrast\",\n \"bridge\",\n \"intensity_alignment\",\n \"structural_balance\",\n \"refresh\"\n ]\n },\n \"score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"primary\": {\n \"type\": \"boolean\"\n }\n },\n \"additionalProperties\": false\n },\n \"explanation_code_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"weight\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"detail\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"risk_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\",\n \"severity\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"severity\": {\n \"type\": \"string\",\n \"enum\": [\n \"low\",\n \"medium\",\n \"high\"\n ]\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"mitigation\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"evidence\": {\n \"type\": \"object\",\n \"properties\": {\n \"method\": {\n \"type\": \"string\",\n \"enum\": [\n \"expert_panel\",\n \"instrumental\",\n \"computed\",\n \"estimated\"\n ]\n },\n \"sources\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n### OGS Explanation Codes\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS pairing JSON document for the described match. It MUST validate against the OGS pairing schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"pairing_slug\": \"brie-champagne\",\n \"dish_ref\": \"ogs:core:dish:brie-on-baguette\",\n \"beverage_ref\": \"ogs:core:beverage:brut-champagne-nv\",\n \"intent\": \"A classic refresh pairing driven by effervescence and acidity against creamy brie.\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/pairing.schema.json", "required_fields": { "id": "ogs:core:pairing:brie-champagne", "ogs_version": "0.1.0", "dish_ref": "ogs:core:dish:brie-on-baguette", "beverage_ref": "ogs:core:beverage:brut-champagne-nv" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie on Baguette with Brut Champagne\",\n \"description\": \"A classic refresh pairing where the effervescence and bright acidity of Brut Champagne cut through the rich, creamy texture of brie.\",\n \"dish_ref\": \"ogs:core:dish:brie-on-baguette\",\n \"beverage_ref\": \"ogs:core:beverage:brut-champagne-nv\",\n \"match_types\": [\n {\n \"type\": \"refresh\",\n \"score\": 92,\n \"description\": \"Carbonation and acidity refresh the palate against creamy brie.\",\n \"primary\": true\n },\n {\n \"type\": \"contrast\",\n \"score\": 88,\n \"description\": \"Crisp, lean Champagne contrasts the rich, fatty cheese.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 85\n }\n ],\n \"overall_score\": 92,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.4,\n \"detail\": \"Champagne bubbles physically scrub the palate between bites of creamy brie.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.3,\n \"detail\": \"High acidity cuts through the fat of the cheese.\"\n },\n {\n \"code\": \"CONTRAST_RICH_CRISP\",\n \"weight\": 0.2,\n \"detail\": \"Rich, creamy brie is balanced by the crisp, lean profile of Brut Champagne.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.1,\n \"detail\": \"Acidity balances the richness of the dish, creating freshness.\"\n }\n ],\n \"risks\": [],\n \"confidence\": 0.92,\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"notes\": \"Widely recognized classic pairing in French gastronomy.\"\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": 5467, "output_tokens": 712, "latency_ms": 8261.5, "usd": 0.135405, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:pairing:brie-champagne\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Brie on Baguette with Brut Champagne NV\",\n \"description\": \"A classic refresh pairing driven by effervescence and acidity against creamy brie.\",\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\": 94,\n \"primary\": true,\n \"description\": \"Bubbles and acidity scrub the palate of creamy brie richness.\"\n },\n {\n \"type\": \"contrast\",\n \"score\": 88,\n \"description\": \"Crisp, lean Champagne contrasts the rich, fatty cheese.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 90,\n \"description\": \"Acidity balances fat; body aligns between cheese and wine.\"\n }\n ],\n \"overall_score\": 92,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"REFRESH_EFFERVESCE\",\n \"weight\": 0.35,\n \"detail\": \"Champagne's fine mousse cleanses the palate between bites of creamy brie.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.25,\n \"detail\": \"High natural acidity cuts through the fat of the cheese.\"\n },\n {\n \"code\": \"CONTRAST_RICH_CRISP\",\n \"weight\": 0.2,\n \"detail\": \"Rich, buttery brie is offset by the crisp, lean profile of Brut Champagne.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.15,\n \"detail\": \"The wine's acidity provides freshness against the dish's richness.\"\n },\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.05,\n \"detail\": \"Both brie and Champagne originate in northern France, reflecting regional affinity.\"\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_INTENSITY_MISMATCH\",\n \"severity\": \"low\",\n \"description\": \"A very ripe, pungent brie could slightly overshadow a delicate NV Champagne.\",\n \"mitigation\": \"Serve brie at cool room temperature and choose a slightly fuller Brut NV.\"\n }\n ],\n \"confidence\": 0.9,\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"notes\": \"Classic, widely validated pairing across sommelier literature.\"\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": 5467, "output_tokens": 913, "latency_ms": 11156.2, "usd": 0.15048, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:pairing:brie-champagne\",\"ogs_version\":\"0.1.0\",\"name\":\"Brie on Baguette with Brut Champagne\",\"description\":\"A classic refresh pairing driven by effervescence and acidity against creamy brie.\",\"dish_ref\":\"ogs:core:dish:brie-on-baguette\",\"beverage_ref\":\"ogs:core:beverage:brut-champagne-nv\",\"match_types\":[{\"type\":\"refresh\",\"score\":95,\"primary\":true,\"description\":\"Bubbles and acidity scrub the palate of creamy fat.\"},{\"type\":\"structural_balance\",\"score\":88,\"description\":\"Champagne acidity balances the richness of brie.\"},{\"type\":\"contrast\",\"score\":85,\"description\":\"Crisp, lean beverage contrasts rich, creamy cheese.\"}],\"overall_score\":92,\"grade\":\"A\",\"explanation_codes\":[{\"code\":\"REFRESH_EFFERVESCE\",\"weight\":0.35,\"detail\":\"Carbonation physically cleanses the palate between bites of creamy brie.\"},{\"code\":\"REFRESH_ACID\",\"weight\":0.25,\"detail\":\"High acidity cuts through the fat of the cheese.\"},{\"code\":\"CONTRAST_RICH_CRISP\",\"weight\":0.2,\"detail\":\"Rich, creamy brie is contrasted by crisp, lean Champagne.\"},{\"code\":\"STRUCT_ACIDITY_BALANCE\",\"weight\":0.2,\"detail\":\"Champagne's acidity balances the richness of the dish.\"}],\"risks\":[],\"confidence\":0.9,\"evidence\":{\"method\":\"expert_panel\",\"notes\":\"Classic sommelier pairing.\"}}", "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": 5467, "output_tokens": 562, "latency_ms": 7517.2, "usd": 0.124155, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 5467.0, "output_tokens_mean": 729.0, "latency_ms_mean": 8978.3, "usd_sum": 0.41004 } }, { "task_id": "ogs:core:benchmark-task:struct-004", "category": "structured_output", "capability": "sensory_profile_json", "difficulty": "medium", "cuisine_region": "indian", "scorer": "json_match", "context_needs": [ "scales.basic_tastes", "scales.structural", "vocab.aromatic_families", "vocab.qualifiers" ], "prompt_template_hash": "9bd6860a8c5c69ec", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nProduce a JSON object representing the sensory profile for ripe mango. The object must have keys basic_tastes (with sweet, sour, salty, bitter, umami), structural (with body, acidity_perception, tannin, astringency, alcohol_heat, effervescence), and aromatics (array of entries with family, group, item, intensity). All intensities on 0-10. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"item\": \"ripe Alphonso mango, peak ripeness\"\n}\n\nANSWER FORMAT: json\n\nRESPONSE JSON SCHEMA:\n{\n \"type\": \"object\",\n \"required\": [\n \"basic_tastes\",\n \"structural\",\n \"aromatics\"\n ],\n \"properties\": {\n \"basic_tastes\": {\n \"type\": \"object\",\n \"required\": [\n \"sweet\",\n \"sour\",\n \"salty\",\n \"bitter\",\n \"umami\"\n ]\n },\n \"structural\": {\n \"type\": \"object\",\n \"required\": [\n \"body\",\n \"acidity_perception\",\n \"tannin\",\n \"astringency\",\n \"alcohol_heat\",\n \"effervescence\"\n ]\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ]\n }\n }\n }\n}", "expected": { "value": { "basic_tastes": { "sweet": 8.5, "sour": 3.0, "salty": 0, "bitter": 0.5, "umami": 0.5 }, "structural": { "body": 5.5, "acidity_perception": 3.0, "tannin": 0, "astringency": 0.5, "alcohol_heat": 0, "effervescence": 0 } }, "required_keys": [ "basic_tastes.sweet", "basic_tastes.sour", "structural.body", "structural.acidity_perception", "structural.tannin" ] }, "samples": [ { "sample": 0, "raw_response": "{\"basic_tastes\":{\"sweet\":8.5,\"sour\":2,\"salty\":0,\"bitter\":0.5,\"umami\":0.5},\"structural\":{\"body\":6.5,\"acidity_perception\":2,\"tannin\":0.5,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"mango\",\"intensity\":9},{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"pineapple\",\"intensity\":4,\"qualifier\":\"ripe\"},{\"family\":\"fruit\",\"group\":\"stone\",\"item\":\"peach\",\"intensity\":3.5},{\"family\":\"floral\",\"group\":\"white_floral\",\"item\":\"orange_blossom\",\"intensity\":2.5},{\"family\":\"spice\",\"group\":\"warm_spice\",\"item\":\"saffron\",\"intensity\":2},{\"family\":\"confection\",\"group\":\"caramel\",\"item\":\"honey\",\"intensity\":3},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"orange\",\"intensity\":2,\"qualifier\":\"zest\"}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.5, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2, "expected": 3.0, "match": true }, "structural.body": { "predicted": 6.5, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0.5, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 1089, "output_tokens": 347, "latency_ms": 4307.2, "usd": 0.04236, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"basic_tastes\":{\"sweet\":8.5,\"sour\":2.5,\"salty\":0,\"bitter\":0.5,\"umami\":0.5},\"structural\":{\"body\":6.5,\"acidity_perception\":2.5,\"tannin\":0.5,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"mango\",\"intensity\":9},{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"pineapple\",\"intensity\":4},{\"family\":\"fruit\",\"group\":\"stone\",\"item\":\"peach\",\"intensity\":3.5},{\"family\":\"floral\",\"group\":\"white_flower\",\"item\":\"honeysuckle\",\"intensity\":3},{\"family\":\"confection\",\"group\":\"caramelized\",\"item\":\"honey\",\"intensity\":3.5},{\"family\":\"spice\",\"group\":\"resinous\",\"item\":\"pine\",\"intensity\":2}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.5, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 6.5, "expected": 5.5, "match": true }, "structural.acidity_perception": { "predicted": 2.5, "expected": 3.0, "match": true }, "structural.tannin": { "predicted": 0.5, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 1089, "output_tokens": 298, "latency_ms": 3890.7, "usd": 0.038685, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"basic_tastes\":{\"sweet\":8.5,\"sour\":2.5,\"salty\":0,\"bitter\":0.5,\"umami\":0.5},\"structural\":{\"body\":6.5,\"acidity_perception\":2.5,\"tannin\":0.5,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"mango\",\"intensity\":9},{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"pineapple\",\"intensity\":4,\"qualifier\":\"ripe\"},{\"family\":\"fruit\",\"group\":\"stone\",\"item\":\"peach\",\"intensity\":3.5},{\"family\":\"floral\",\"group\":\"white_floral\",\"item\":\"orange_blossom\",\"intensity\":2.5},{\"family\":\"spice\",\"group\":\"resinous\",\"item\":\"pine_resin\",\"intensity\":1.5},{\"family\":\"confection\",\"group\":\"caramelized\",\"item\":\"honey\",\"intensity\":3}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.sweet": { "predicted": 8.5, "expected": 8.5, "match": true }, "basic_tastes.sour": { "predicted": 2.5, "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": 0.5, "expected": 0, "match": true } } }, "metrics": { "input_tokens": 1089, "output_tokens": 315, "latency_ms": 4202.6, "usd": 0.03996, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 1089.0, "output_tokens_mean": 320.0, "latency_ms_mean": 4133.5, "usd_sum": 0.121005 } }, { "task_id": "ogs:core:benchmark-task:struct-005", "category": "structured_output", "capability": "schema_valid_dish", "difficulty": "expert", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.dish", "vocab.component_roles", "vocab.cooking_methods", "vocab.courses", "vocab.service_temperatures", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "9caf9bc474b2464d", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS dish schema (`schema/dish.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/dish.schema.json\",\n \"title\": \"OGS Dish\",\n \"description\": \"A composed dish with components, cooking methods, and overall sensory profile.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"components\",\n \"overall_sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"cuisine\": {\n \"type\": \"string\",\n \"description\": \"Free-text cuisine name (v0.1) OR a cuisine entity reference matching ogs::cuisine: (v0.2+).\"\n },\n \"course\": {\n \"type\": \"string\",\n \"enum\": [\n \"amuse\",\n \"appetizer\",\n \"soup\",\n \"salad\",\n \"fish\",\n \"main\",\n \"cheese\",\n \"dessert\",\n \"petit_four\"\n ]\n },\n \"service_temperature\": {\n \"type\": \"string\",\n \"enum\": [\n \"frozen\",\n \"cold\",\n \"cool\",\n \"room\",\n \"warm\",\n \"hot\",\n \"very_hot\"\n ]\n },\n \"components\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/component\"\n }\n },\n \"overall_sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"component\": {\n \"type\": \"object\",\n \"required\": [\n \"role\",\n \"ingredient_ref\"\n ],\n \"properties\": {\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"main_protein\",\n \"main_vegetable\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n ]\n },\n \"ingredient_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\"\n },\n \"cooking_method\": {\n \"type\": \"string\",\n \"enum\": [\n \"raw\",\n \"seared\",\n \"grilled\",\n \"roasted\",\n \"braised\",\n \"poached\",\n \"steamed\",\n \"fried\",\n \"confit\",\n \"smoked\",\n \"fermented\",\n \"cured\",\n \"pickled\",\n \"dehydrated\",\n \"sous_vide\",\n \"blanched\",\n \"sauteed\",\n \"baked\",\n \"charred\",\n \"emulsified\"\n ]\n },\n \"maillard_index\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"reduction_level\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"proportion\": {\n \"type\": \"string\",\n \"enum\": [\n \"dominant\",\n \"significant\",\n \"accent\",\n \"trace\"\n ]\n },\n \"sensory_contribution\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS dish JSON document for 'moules marinieres' (mussels steamed with white wine, shallots, parsley, butter). It must validate against the OGS dish schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"dish_slug\": \"moules-marinieres\",\n \"cuisine\": \"french\",\n \"course\": \"main\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/dish.schema.json", "required_fields": { "id": "ogs:core:dish:moules-marinieres", "ogs_version": "0.1.0" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Moules Marinières\",\n \"description\": \"Mussels steamed with white wine, shallots, butter, and parsley.\",\n \"cuisine\": \"french\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:blue-mussel\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 6,\n \"umami\": 7\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\"tender\", \"juicy\"]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"poached\",\n \"reduction_level\": 2,\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sour\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"tree_fruit\",\n \"item\": \"green_apple\",\n \"intensity\": 3\n }\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n }\n ]\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\"creamy\", \"silky\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\n \"family\": \"herbal\",\n \"group\": \"fresh_herb\",\n \"item\": \"parsley\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5\n }\n ]\n }\n },\n {\n \"role\": \"seasoning\",", "compliant": false, "score": 0.0, "detail": { "error": "no_json" }, "metrics": { "input_tokens": 4573, "output_tokens": 1024, "latency_ms": 9819.0, "usd": 0.145395, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"fr\",\n \"available_languages\": [\"fr\", \"en\"],\n \"name\": {\n \"fr\": \"Moules marinières\",\n \"en\": \"Mussels mariniere\"\n },\n \"description\": {\n \"fr\": \"Moules cuites à la vapeur dans un bouillon de vin blanc, échalotes, persil et beurre.\",\n \"en\": \"Mussels steamed in a broth of white wine, shallots, parsley, and butter.\"\n },\n \"cuisine\": \"french\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:mussel\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 6.5,\n \"umami\": 7,\n \"sweet\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"shellfish\",\n \"item\": \"mussel\",\n \"qualifier\": \"cooked\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\"tender\", \"plump\", \"slightly_chewy\"]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"steamed\",\n \"reduction_level\": 2,\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sour\": 5,\n \"umami\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"orchard\",\n \"item\": \"green_apple\",\n \"intensity\": 3\n }\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sweet\": 3\n },\n \"aromatics\": [\n {\n \"family\": \"vegetal\",\n \"group\": \"allium\",\n \"item\": \"shallot\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n }\n ]\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"cooking_method\": \"emulsified\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 2,\n \"umami\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"dairy\",\n \"group\": \"butter\",\n \"item\": \"butter\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n }\n ],\n \"texture\": [\"creamy\", \"rich\"]", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "['fr', 'en'] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:dish:moules-marinieres", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false } } }, "metrics": { "input_tokens": 4573, "output_tokens": 1024, "latency_ms": 10372.3, "usd": 0.145395, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:dish:moules-marinieres\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Moules Marinières\",\n \"description\": \"Mussels steamed with white wine, shallots, butter, and parsley.\",\n \"cuisine\": \"french\",\n \"course\": \"main\",\n \"service_temperature\": \"hot\",\n \"components\": [\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:mussel\",\n \"cooking_method\": \"steamed\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 6,\n \"umami\": 7\n },\n \"aromatics\": [\n {\"family\": \"marine\", \"group\": \"shellfish\", \"item\": \"mussel\", \"intensity\": 7}\n ],\n \"texture\": [\"tender\", \"plump\"]\n }\n },\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:white-wine\",\n \"cooking_method\": \"poached\",\n \"reduction_level\": 2,\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"sour\": 5\n },\n \"aromatics\": [\n {\"family\": \"fruit\", \"group\": \"orchard\", \"item\": \"apple\", \"intensity\": 3}\n ]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:shallot\",\n \"cooking_method\": \"sauteed\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\"family\": \"vegetal\", \"group\": \"allium\", \"item\": \"shallot\", \"qualifier\": \"cooked\", \"intensity\": 5}\n ]\n }\n },\n {\n \"role\": \"fat_component\",\n \"ingredient_ref\": \"ogs:core:ingredient:butter\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\"family\": \"dairy\", \"group\": \"butter\", \"item\": \"butter\", \"intensity\": 4}\n ],\n \"texture\": [\"creamy\"]\n }\n },\n {\n \"role\": \"aromatic_garnish\",\n \"ingredient_ref\": \"ogs:core:ingredient:parsley\",\n \"cooking_method\": \"raw\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"aromatics\": [\n {\"family\": \"herbal\", \"group\": \"green-herb\", \"item\": \"parsley\", \"qualifier\": \"fresh\", \"intensity\": 5}\n ]\n }\n },\n {\n \"role\": \"seasoning\",\n \"ingredient_ref\": \"ogs:core:ingredient:black-pepper\",\n \"proportion\": \"trace\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\"bitter\": 1},\n \"aromatics\": [\n {\"family\": \"spice\", \"group\": \"pepper\", \"item\": \"black-pepper\", \"", "compliant": false, "score": 0.0, "detail": { "error": "no_json" }, "metrics": { "input_tokens": 4573, "output_tokens": 1024, "latency_ms": 10163.2, "usd": 0.145395, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } } ], "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": 0.3333, "metrics": { "input_tokens_mean": 4573.0, "output_tokens_mean": 1024.0, "latency_ms_mean": 10118.167, "usd_sum": 0.436185 } }, { "task_id": "ogs:core:benchmark-task:struct-006", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "medium", "cuisine_region": "iranian", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "bb4d0fcee2d1e751", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'saffron' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"saffron\",\n \"namespace\": \"core\",\n \"id_slug\": \"saffron-stigma\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:saffron-stigma", "ogs_version": "0.1.0", "category": "spice" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:saffron-stigma\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"available_languages\": [\"en\"],\n \"name\": \"saffron\",\n \"description\": \"Dried stigmas of Crocus sativus, prized for their golden color, honeyed aroma, and slightly bitter, hay-like flavor.\",\n \"category\": \"spice\",\n \"subcategory\": \"dried stigma\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 0,\n \"salty\": 0,\n \"bitter\": 4,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 0,\n \"astringency\": 2\n },\n \"aromatics\": [\n {\"family\": \"floral\", \"group\": \"dried flower\", \"item\": \"saffron\", \"qualifier\": \"dried\", \"intensity\": 8},\n {\"family\": \"herbal\", \"group\": \"hay\", \"item\": \"hay\", \"qualifier\": \"dried\", \"intensity\": 6},\n {\"family\": \"confection\", \"group\": \"honey\", \"item\": \"honey\", \"intensity\": 4},\n {\"family\": \"earth\", \"group\": \"earthy\", \"item\": \"iodine\", \"intensity\": 3},\n {\"family\": \"spice\", \"group\": \"warm spice\", \"item\": \"saffron\", \"qualifier\": \"dried\", \"intensity\": 7}\n ],\n \"texture\": [\"brittle\", \"thread-like\"],\n \"finish_length\": 8,\n \"complexity\": 8\n },\n \"origin\": {\n \"region\": \"Iran, Spain (La Mancha), Kashmir, Afghanistan, Greece\",\n \"season\": \"autumn harvest\",\n \"terroir_notes\": \"Highest quality threads are deep crimson with orange tips; grown in arid, calcareous soils.\"\n },\n \"notes\": \"Bloom in warm liquid before use to extract color and aroma. A small pinch is sufficient; excess becomes medicinal and bitter.\",\n \"metadata\": {\n \"source\": \"OGS core reference dataset\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient: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": 3776, "output_tokens": 726, "latency_ms": 9261.3, "usd": 0.11109, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:ingredient:saffron-stigma\",\"ogs_version\":\"0.1.0\",\"name\":\"saffron\",\"category\":\"spice\",\"subcategory\":\"dried stigma\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":1.5,\"sour\":0,\"salty\":0,\"bitter\":4,\"umami\":1},\"structural\":{\"body\":3,\"acidity_perception\":0,\"tannin\":1.5,\"astringency\":2,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"floral\",\"group\":\"dried flower\",\"item\":\"saffron\",\"qualifier\":\"dried\",\"intensity\":8.5},{\"family\":\"spice\",\"group\":\"warm spice\",\"item\":\"saffron\",\"intensity\":7},{\"family\":\"earth\",\"group\":\"hay\",\"item\":\"hay\",\"qualifier\":\"dried\",\"intensity\":5.5},{\"family\":\"confection\",\"group\":\"honey\",\"item\":\"honey\",\"intensity\":3},{\"family\":\"wood\",\"group\":\"resin\",\"item\":\"leather\",\"intensity\":3}],\"texture\":[\"thread-like\",\"brittle\",\"dry\"],\"finish_length\":8,\"complexity\":8.5},\"origin\":{\"region\":\"Iran, Kashmir, La Mancha (Spain)\",\"season\":\"autumn harvest\",\"terroir_notes\":\"Crocus sativus stigmas hand-harvested and dried; flavor depends on crocin, picrocrocin, and safranal content.\"},\"notes\":\"Bloom in warm liquid to extract color and aroma; extremely potent, use sparingly.\"}", "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": 3776, "output_tokens": 503, "latency_ms": 7868.3, "usd": 0.094365, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:ingredient:saffron-stigma\",\"ogs_version\":\"0.1.0\",\"name\":\"saffron\",\"category\":\"spice\",\"subcategory\":\"stigma\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":1.5,\"sour\":0,\"salty\":0,\"bitter\":4,\"umami\":0.5},\"structural\":{\"body\":3,\"acidity_perception\":0,\"tannin\":1,\"astringency\":1.5,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"floral\",\"group\":\"dried-flower\",\"item\":\"saffron\",\"qualifier\":\"dried\",\"intensity\":8},{\"family\":\"earth\",\"group\":\"hay\",\"item\":\"hay\",\"qualifier\":\"dried\",\"intensity\":6},{\"family\":\"spice\",\"group\":\"warm-spice\",\"item\":\"honeyed-spice\",\"intensity\":5},{\"family\":\"confection\",\"group\":\"honey\",\"item\":\"honey\",\"intensity\":3},{\"family\":\"wood\",\"group\":\"resinous\",\"item\":\"leather\",\"intensity\":2.5}],\"texture\":[\"thread-like\",\"brittle\",\"dry\"],\"finish_length\":8,\"complexity\":8.5},\"origin\":{\"region\":\"Iran, Spain (La Mancha), Kashmir\",\"season\":\"autumn harvest\",\"terroir_notes\":\"Hand-harvested stigmas of Crocus sativus; flavor driven by safranal, picrocrocin, and crocin.\"},\"notes\":\"Use sparingly; bloom in warm liquid to extract color and aroma.\"}", "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": 3776, "output_tokens": 499, "latency_ms": 7752.4, "usd": 0.094065, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3776.0, "output_tokens_mean": 576.0, "latency_ms_mean": 8294.0, "usd_sum": 0.29952 } }, { "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": "{\"id\":\"ogs:core:ingredient:aka-miso\",\"ogs_version\":\"0.1.0\",\"name\":\"miso (red)\",\"category\":\"other\",\"subcategory\":\"fermented soybean paste\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":2,\"sour\":1.5,\"salty\":8.5,\"bitter\":2,\"umami\":9},\"structural\":{\"body\":8,\"acidity_perception\":1.5,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"savory\",\"group\":\"fermented\",\"item\":\"soybean\",\"qualifier\":\"fermented\",\"intensity\":8.5},{\"family\":\"savory\",\"group\":\"meaty\",\"item\":\"broth\",\"intensity\":6},{\"family\":\"earth\",\"group\":\"earthy\",\"item\":\"soil\",\"intensity\":4},{\"family\":\"confection\",\"group\":\"caramel\",\"item\":\"molasses\",\"intensity\":3.5},{\"family\":\"savory\",\"group\":\"yeasty\",\"item\":\"yeast\",\"qualifier\":\"fermented\",\"intensity\":4}],\"texture\":[\"paste\",\"dense\",\"smooth\"],\"finish_length\":7.5,\"complexity\":7.5}}", "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": 3778, "output_tokens": 383, "latency_ms": 4772.1, "usd": 0.085395, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"available_languages\": [\"en\", \"ja\"],\n \"name\": {\n \"en\": \"Red miso\",\n \"ja\": \"赤味噌\"\n },\n \"description\": {\n \"en\": \"Aka miso, a long-aged Japanese fermented soybean paste with a deep reddish-brown color, robust umami, and pronounced salinity.\"\n },\n \"category\": \"other\",\n \"subcategory\": \"fermented-paste\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 1.5,\n \"salty\": 8,\n \"bitter\": 2.5,\n \"umami\": 9\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 1.5,\n \"tannin\": 0,\n \"astringency\": 2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soybean paste\",\n \"qualifier\": \"fermented\",\n \"intensity\": 9\n },\n {\n \"family\": \"savory\",\n \"group\": \"broth\",\n \"item\": \"meaty broth\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"roasted\",\n \"item\": \"toasted grain\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"molasses\",\n \"intensity\": 4\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"prune\",\n \"qualifier\": \"dried\",\n \"intensity\": 2.5\n }\n ],\n \"texture\": [\"paste\", \"smooth\", \"dense\", \"slightly-grainy\"],\n \"finish_length\": 8,\n \"complexity\": 8\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Japan (notably Tohoku and Aichi regions)\",\n \"ja\": \"日本(東北・愛知)\"\n },\n \"season\": {\n \"en\": \"Year-round; traditionally aged 1-3 years\"\n },\n \"terroir_notes\": {\n \"en\": \"Long fermentation with higher soybean-to-koji ratio and elevated salt develops darker color and deeper umami compared to white (shiro) miso.\"\n }\n },\n \"notes\": {\n \"en\": \"Use sparingly as a seasoning base for hearty soups, braises, marinades, and glazes; its strong salinity and umami can dominate delicate preparations.\"\n },\n \"metadata\": {\n \"source\": \"OGS core reference dataset\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient: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": 3778, "output_tokens": 960, "latency_ms": 32553.7, "usd": 0.12867, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:aka-miso\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"ja\",\n \"available_languages\": [\"ja\", \"en\"],\n \"name\": {\n \"ja\": \"赤味噌\",\n \"en\": \"Red Miso\"\n },\n \"description\": {\n \"en\": \"A long-fermented Japanese soybean paste, aged from several months to years, yielding a deep reddish-brown color, assertive salinity, and pronounced umami with funky, savory depth.\",\n \"ja\": \"長期熟成された赤褐色の大豆発酵調味料で、強い塩味と旨味、濃厚な風味が特徴。\"\n },\n \"category\": \"other\",\n \"subcategory\": \"fermented-paste\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 2,\n \"salty\": 8.5,\n \"bitter\": 3,\n \"umami\": 9\n },\n \"structural\": {\n \"body\": 8,\n \"acidity_perception\": 2,\n \"astringency\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"fermented\",\n \"item\": \"soybean-paste\",\n \"qualifier\": \"fermented\",\n \"intensity\": 9\n },\n {\n \"family\": \"savory\",\n \"group\": \"broth\",\n \"item\": \"meaty-broth\",\n \"intensity\": 6\n },\n {\n \"family\": \"earth\",\n \"group\": \"earthy\",\n \"item\": \"damp-earth\",\n \"intensity\": 4\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"molasses\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"wood\",\n \"group\": \"aged\",\n \"item\": \"barrel\",\n \"qualifier\": \"fermented\",\n \"intensity\": 2.5\n }\n ],\n \"texture\": [\"paste\", \"dense\", \"smooth\", \"slightly-grainy\"],\n \"finish_length\": 8,\n \"complexity\": 8.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Japan (notably Sendai, Aichi, and northern Honshu)\",\n \"ja\": \"日本(仙台、愛知、東北地方)\"\n },\n \"season\": {\n \"en\": \"year-round (aged product)\"\n },\n \"terroir_notes\": {\n \"en\": \"Aged red miso develops deeper color and umami through prolonged Maillard reactions during extended koji fermentation, often 1-3 years.\"\n }\n },\n \"notes\": {\n \"en\": \"Use sparingly due to high salinity; excellent in hearty soups, braises, glazes, and marinades where its depth can anchor rich flavors.\"\n },\n \"metadata\": {\n \"source\": \"OGS core dataset\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient: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": 3778, "output_tokens": 970, "latency_ms": 15433.5, "usd": 0.12942, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3778.0, "output_tokens_mean": 771.0, "latency_ms_mean": 17586.433, "usd_sum": 0.343485 } }, { "task_id": "ogs:core:benchmark-task:struct-008", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "hard", "cuisine_region": "turkish", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "791ac1beebd95233", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'Urfa chili' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"Urfa chili\",\n \"namespace\": \"core\",\n \"id_slug\": \"urfa-biber\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:urfa-biber", "ogs_version": "0.1.0", "category": "spice" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"available_languages\": [\"en\", \"tr\"],\n \"name\": {\n \"en\": \"Urfa chili\",\n \"tr\": \"Urfa biberi\"\n },\n \"description\": {\n \"en\": \"A Turkish dried chili pepper (isot) from the Urfa region, sun-dried by day and sweated by night, yielding a dark purple-black flake with raisin-like, smoky, and earthy character and moderate heat.\"\n },\n \"category\": \"spice\",\n \"subcategory\": \"dried chili\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 1.5,\n \"salty\": 0.5,\n \"bitter\": 3,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 1.5,\n \"astringency\": 2,\n \"alcohol_heat\": 4.5\n },\n \"aromatics\": [\n {\"family\": \"fruit\", \"group\": \"dried fruit\", \"item\": \"raisin\", \"qualifier\": \"dried\", \"intensity\": 7},\n {\"family\": \"fruit\", \"group\": \"dried fruit\", \"item\": \"prune\", \"qualifier\": \"dried\", \"intensity\": 5.5},\n {\"family\": \"wood\", \"group\": \"smoke\", \"item\": \"wood smoke\", \"intensity\": 5},\n {\"family\": \"earth\", \"group\": \"earthy\", \"item\": \"tobacco\", \"qualifier\": \"dried\", \"intensity\": 4.5},\n {\"family\": \"confection\", \"group\": \"caramel\", \"item\": \"molasses\", \"intensity\": 4},\n {\"family\": \"spice\", \"group\": \"chili\", \"item\": \"dried chili\", \"qualifier\": \"dried\", \"intensity\": 6.5},\n {\"family\": \"confection\", \"group\": \"chocolate\", \"item\": \"dark chocolate\", \"intensity\": 3}\n ],\n \"texture\": [\"coarse flake\", \"slightly oily\", \"moist\", \"chewy\"],\n \"finish_length\": 7,\n \"complexity\": 7.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Şanlıurfa Province, southeastern Turkey\",\n \"tr\": \"Şanlıurfa, Türkiye\"\n },\n \"season\": {\n \"en\": \"Harvested late summer to early autumn; dried and cured before use\"\n },\n \"terroir_notes\": {\n \"en\": \"Traditional two-stage curing: peppers are sun-dried during the day and wrapped to sweat at night, producing the characteristic dark color, moist texture, and fermented raisin-like aroma.\"\n }\n },\n \"notes\": {\n \"en\": \"Also known as isot biber. Moderately hot (roughly 30,000-50,000 SHU) with a slow-building, lingering heat rather than a sharp front-palate burn. Often salted during processing; check label before adding salt to dishes.\"\n },\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic prof", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "['en', 'tr'] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:ingredient:urfa-biber", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "category": { "predicted": null, "expected": "spice", "match": false } } }, "metrics": { "input_tokens": 3781, "output_tokens": 1024, "latency_ms": 13569.0, "usd": 0.133515, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"tr\",\n \"available_languages\": [\"tr\", \"en\"],\n \"name\": {\n \"tr\": \"Urfa biber\",\n \"en\": \"Urfa chili\"\n },\n \"description\": {\n \"en\": \"A sun-dried, semi-moist Turkish chili pepper from the Urfa region, known for its dark burgundy color, smoky raisin-like sweetness, and slow-building mild heat.\",\n \"tr\": \"Urfa yöresine özgü, güneşte kurutulmuş, koyu bordo renkli, dumanlı ve kuru üzüm notalı, hafif acılı pul biber.\"\n },\n \"category\": \"spice\",\n \"subcategory\": \"dried chili\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 1.5,\n \"salty\": 0.5,\n \"bitter\": 2,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 1.5,\n \"tannin\": 2,\n \"astringency\": 2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"raisin\",\n \"qualifier\": \"dried\",\n \"intensity\": 7\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried fruit\",\n \"item\": \"prune\",\n \"qualifier\": \"dried\",\n \"intensity\": 5\n },\n {\n \"family\": \"wood\",\n \"group\": \"smoke\",\n \"item\": \"wood smoke\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"earth\",\n \"group\": \"roasted\",\n \"item\": \"tobacco\",\n \"qualifier\": \"dried\",\n \"intensity\": 4\n },\n {\n \"family\": \"spice\",\n \"group\": \"chili\",\n \"item\": \"capsicum\",\n \"qualifier\": \"dried\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"molasses\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\"coarse flake\", \"semi-moist\", \"oily\"],\n \"finish_length\": 7,\n \"complexity\": 7.5\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Şanlıurfa Province, southeastern Turkey\",\n \"tr\": \"Şanlıurfa, Güneydoğu Anadolu\"\n },\n \"season\": {\n \"en\": \"Harvested late summer; dried and cured through early autumn\"\n },\n \"terroir_notes\": {\n \"en\": \"Peppers are sun-dried by day and wrapped tightly at night to sweat, concentrating sugars and developing the characteristic dark color and raisin-like aroma.\"\n }\n },\n \"notes\": {\n \"en\": \"Traditionally salted during", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "['tr', 'en'] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:ingredient:urfa-biber", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "category": { "predicted": null, "expected": "spice", "match": false } } }, "metrics": { "input_tokens": 3781, "output_tokens": 1024, "latency_ms": 13736.7, "usd": 0.133515, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:urfa-biber\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"available_languages\": [\"en\", \"tr\"],\n \"name\": {\n \"en\": \"Urfa chili\",\n \"tr\": \"Urfa biberi\"\n },\n \"description\": {\n \"en\": \"A Turkish chili pepper (isot biber) from the Urfa region, sun-dried by day and sweated by night, yielding dark burgundy flakes with raisin-like, smoky, and earthy notes and a slow-building moderate heat.\"\n },\n \"category\": \"spice\",\n \"subcategory\": \"dried chili\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 1.5,\n \"salty\": 1,\n \"bitter\": 2,\n \"umami\": 3.5\n },\n \"structural\": {\n \"body\": 5,\n \"acidity_perception\": 1.5,\n \"tannin\": 2,\n \"astringency\": 2,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\"family\": \"fruit\", \"group\": \"dried fruit\", \"item\": \"raisin\", \"qualifier\": \"dried\", \"intensity\": 6.5},\n {\"family\": \"fruit\", \"group\": \"dried fruit\", \"item\": \"prune\", \"qualifier\": \"dried\", \"intensity\": 5},\n {\"family\": \"wood\", \"group\": \"smoke\", \"item\": \"wood smoke\", \"intensity\": 4},\n {\"family\": \"earth\", \"group\": \"earthy\", \"item\": \"tobacco\", \"qualifier\": \"dried\", \"intensity\": 4},\n {\"family\": \"spice\", \"group\": \"chili\", \"item\": \"chili pepper\", \"qualifier\": \"dried\", \"intensity\": 6},\n {\"family\": \"confection\", \"group\": \"caramel\", \"item\": \"molasses\", \"intensity\": 3}\n ],\n \"texture\": [\"coarse flake\", \"slightly oily\", \"moist\"],\n \"finish_length\": 7,\n \"complexity\": 7\n },\n \"origin\": {\n \"region\": {\n \"en\": \"Şanlıurfa Province, southeastern Turkey\",\n \"tr\": \"Şanlıurfa, Türkiye\"\n },\n \"season\": {\n \"en\": \"Harvested late summer to early autumn; cured over several weeks\"\n },\n \"terroir_notes\": {\n \"en\": \"Traditional isot curing: sun-dried during the day and wrapped to sweat overnight, producing a dark, almost black-purple flake with concentrated fruit and smoke character.\"\n }\n },\n \"notes\": {\n \"en\": \"Heat is moderate and slow-building (roughly 30,000-50,000 SHU); often finished with salt and sunflower oil. Pairs well with lamb, eggplant, yogurt, and tomato-based dishes.\"\n },\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic ingredient card\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient: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": 3781, "output_tokens": 1018, "latency_ms": 13076.4, "usd": 0.133065, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 3781.0, "output_tokens_mean": 1022.0, "latency_ms_mean": 13460.7, "usd_sum": 0.400095 } }, { "task_id": "ogs:core:benchmark-task:struct-009", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "easy", "cuisine_region": "american", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "a6a51cef64e43626", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'Meyer lemon' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"Meyer lemon\",\n \"namespace\": \"core\",\n \"id_slug\": \"meyer-lemon\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:meyer-lemon", "ogs_version": "0.1.0", "category": "fruit" } }, "samples": [ { "sample": 0, "raw_response": "{\"id\":\"ogs:core:ingredient:meyer-lemon\",\"ogs_version\":\"0.1.0\",\"name\":\"Meyer lemon\",\"category\":\"fruit\",\"subcategory\":\"citrus\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3.5,\"sour\":7,\"salty\":0,\"bitter\":1.5,\"umami\":0},\"structural\":{\"body\":3,\"acidity_perception\":7,\"astringency\":1},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"fresh\",\"intensity\":7.5},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"mandarin\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"floral\",\"group\":\"white flower\",\"item\":\"orange blossom\",\"intensity\":4},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"zest\",\"intensity\":6}],\"texture\":[\"juicy\",\"tender\"],\"finish_length\":5,\"complexity\":6},\"description\":\"A sweeter, less acidic citrus believed to be a cross between a standard lemon and a mandarin or orange, with thin, fragrant skin and floral aromatics.\"}", "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": 3784, "output_tokens": 394, "latency_ms": 5661.1, "usd": 0.08631, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:meyer-lemon\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"available_languages\": [\"en\"],\n \"name\": {\"en\": \"Meyer lemon\"},\n \"description\": {\"en\": \"A small, round citrus fruit believed to be a cross between a lemon and a mandarin or common orange. Meyer lemons have thin, fragrant, deep yellow-orange skin and sweeter, less acidic juice than standard lemons.\"},\n \"category\": \"fruit\",\n \"subcategory\": \"citrus\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3,\n \"sour\": 6,\n \"salty\": 0,\n \"bitter\": 1.5,\n \"umami\": 0\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 6.5,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\"family\": \"fruit\", \"group\": \"citrus\", \"item\": \"meyer lemon zest\", \"qualifier\": \"zest\", \"intensity\": 8},\n {\"family\": \"fruit\", \"group\": \"citrus\", \"item\": \"mandarin\", \"qualifier\": \"fresh\", \"intensity\": 5},\n {\"family\": \"fruit\", \"group\": \"citrus\", \"item\": \"lemon\", \"qualifier\": \"fresh\", \"intensity\": 6.5},\n {\"family\": \"floral\", \"group\": \"white flowers\", \"item\": \"orange blossom\", \"qualifier\": \"fresh\", \"intensity\": 4},\n {\"family\": \"herbal\", \"group\": \"green\", \"item\": \"thyme-like herbal\", \"qualifier\": \"fresh\", \"intensity\": 2}\n ],\n \"texture\": [\"juicy\", \"tender rind\", \"thin-skinned\"],\n \"finish_length\": 6,\n \"complexity\": 6.5\n },\n \"origin\": {\n \"region\": {\"en\": \"Originally from China; widely cultivated in California and the Mediterranean\"},\n \"season\": {\"en\": \"Late autumn through early spring (Northern Hemisphere)\"},\n \"terroir_notes\": {\"en\": \"Thrives in mild Mediterranean climates; thin skin and delicate flesh make fruit best suited to local markets.\"}\n },\n \"notes\": {\"en\": \"Prized in pastry and cocktails for its aromatic zest and rounded, less sharp acidity. Both juice and zest are used; rind is edible when unwaxed.\"},\n \"metadata\": {\n \"source\": \"OGS core reference dataset\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient: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": 3784, "output_tokens": 901, "latency_ms": 11938.2, "usd": 0.124335, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:ingredient:meyer-lemon\",\"ogs_version\":\"0.1.0\",\"name\":\"Meyer lemon\",\"category\":\"fruit\",\"subcategory\":\"citrus\",\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3,\"sour\":7,\"salty\":0,\"bitter\":1.5,\"umami\":0},\"structural\":{\"body\":3,\"acidity_perception\":7,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"fresh\",\"intensity\":7.5},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"mandarin\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"floral\",\"group\":\"blossom\",\"item\":\"orange blossom\",\"intensity\":4},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon zest\",\"qualifier\":\"zest\",\"intensity\":6}],\"texture\":[\"juicy\",\"tender\"],\"finish_length\":5,\"complexity\":6},\"description\":\"A hybrid citrus fruit believed to be a cross between a lemon and a mandarin or orange, with thinner, fragrant skin, sweeter and less acidic juice than a common lemon, and floral aromatics.\"}", "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": 3784, "output_tokens": 436, "latency_ms": 5789.4, "usd": 0.08946, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3784.0, "output_tokens_mean": 577.0, "latency_ms_mean": 7796.233, "usd_sum": 0.300105 } }, { "task_id": "ogs:core:benchmark-task:struct-010", "category": "structured_output", "capability": "schema_valid_ingredient", "difficulty": "hard", "cuisine_region": "mexican", "scorer": "schema_validation", "context_needs": [ "schema.ingredient", "vocab.ingredient_categories", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "6d4d6d3cc23f3283", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS ingredient schema (`schema/ingredient.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/ingredient.schema.json\",\n \"title\": \"OGS Ingredient\",\n \"description\": \"An ingredient entity with sensory profile, category, and provenance metadata.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"category\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\",\n \"description\": \"OGS identifier in the format ogs::ingredient:\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\",\n \"description\": \"OGS specification version (0.1.x or 0.2.x)\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\",\n \"description\": \"Authoritative / endonym language of this entity's human-readable fields.\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"description\": \"Advisory list of languages covered by this entity's LString fields.\"\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"protein\",\n \"vegetable\",\n \"fruit\",\n \"grain\",\n \"dairy\",\n \"fat\",\n \"herb\",\n \"spice\",\n \"fungus\",\n \"legume\",\n \"nut\",\n \"seed\",\n \"sweetener\",\n \"acid\",\n \"salt\",\n \"other\"\n ]\n },\n \"subcategory\": {\n \"type\": \"string\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"origin\": {\n \"type\": \"object\",\n \"properties\": {\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"season\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"terroir_notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Ingredient categories\n\nprotein, vegetable, fruit, grain, dairy, fat, herb, spice, fungus, legume, nut, seed, sweetener, acid, salt, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document that describes 'wild huitlacoche' as an OGS ingredient. It MUST validate against the OGS ingredient schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"ingredient_name\": \"wild huitlacoche\",\n \"namespace\": \"core\",\n \"id_slug\": \"huitlacoche\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/ingredient.schema.json", "required_fields": { "id": "ogs:core:ingredient:huitlacoche", "ogs_version": "0.1.0", "category": "fungus" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"es-MX\",\n \"available_languages\": [\"es-MX\", \"en\"],\n \"name\": {\n \"es-MX\": \"huitlacoche silvestre\",\n \"en\": \"wild huitlacoche\"\n },\n \"description\": {\n \"es-MX\": \"Hongo Ustilago maydis que crece de forma silvestre sobre mazorcas de maíz, apreciado en la cocina mexicana por su sabor terroso y umami profundo.\",\n \"en\": \"Ustilago maydis, a fungus that grows wild on ears of corn, prized in Mexican cuisine for its earthy, deeply umami flavor.\"\n },\n \"category\": \"fungus\",\n \"subcategory\": \"corn smut\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.0,\n \"sour\": 0.5,\n \"salty\": 1.0,\n \"bitter\": 1.5,\n \"umami\": 8.0\n },\n \"structural\": {\n \"body\": 7.0,\n \"acidity_perception\": 0.5,\n \"tannin\": 1.0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"fungal\",\n \"item\": \"mushroom\",\n \"qualifier\": \"fresh\",\n \"intensity\": 8.0\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"damp earth\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"grain\",\n \"item\": \"fresh corn\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"savory\",\n \"group\": \"umami\",\n \"item\": \"mushroom broth\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"wood\",\n \"group\": \"smoke\",\n \"item\": \"sweet smoke\",\n \"intensity\": 3.0\n }\n ],\n \"texture\": [\"tender\", \"juicy\", \"yielding\", \"slightly chewy\"],\n \"finish_length\": 7.0,\n \"complexity\": 8.0\n },\n \"origin\": {\n \"region\": {\n \"es-MX\": \"México central (Milpa Alta, Estado de México, Tlaxcala, Puebla)\",\n \"en\": \"Central Mexico (Milpa Alta, State of Mexico, Tlaxcala, Puebla)\"\n },\n \"season\": {\n \"es-MX\": \"temporada de lluvias (junio a septiembre)\",\n \"en\": \"rainy season (June to September)\"\n },\n \"terroir_notes\": {\n \"en\": \"Wild huitlacoche develops on rain-fed milpa corn during the wet season; highly perishable, traditionally harvested within days of formation while the galls are still soft and dark.\"\n }\n },\n \"notes\": {\n \"en\": \"Also called 'Mexican truffle'", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "['es-MX', 'en'] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:ingredient:huitlacoche", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "category": { "predicted": null, "expected": "fungus", "match": false } } }, "metrics": { "input_tokens": 3785, "output_tokens": 1024, "latency_ms": 12952.9, "usd": 0.133575, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"wild huitlacoche\",\n \"description\": \"Huitlacoche, also known as corn smut, is an edible fungus (Ustilago maydis) that grows on ears of maize. Prized in Mexican cuisine, wild-harvested huitlacoche has a smoky, earthy, mushroomy flavor with sweet corn undertones.\",\n \"category\": \"fungus\",\n \"subcategory\": \"corn smut\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 2.5,\n \"sour\": 0.5,\n \"salty\": 1,\n \"bitter\": 1.5,\n \"umami\": 7.5\n },\n \"structural\": {\n \"body\": 6.5,\n \"acidity_perception\": 0.5,\n \"tannin\": 0,\n \"astringency\": 1,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"black mushroom\",\n \"intensity\": 8\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"damp earth\",\n \"intensity\": 6\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"starchy\",\n \"item\": \"sweet corn\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"savory\",\n \"group\": \"smoky\",\n \"item\": \"wood smoke\",\n \"intensity\": 4\n },\n {\n \"family\": \"wood\",\n \"group\": \"char\",\n \"item\": \"charred husk\",\n \"intensity\": 3.5\n }\n ],\n \"texture\": [\n \"soft\",\n \"tender\",\n \"yielding\",\n \"slightly slimy when cooked\",\n \"inky\"\n ],\n \"finish_length\": 6.5,\n \"complexity\": 7.5\n },\n \"origin\": {\n \"region\": \"Mexico (Central Highlands, traditional milpa fields)\",\n \"season\": \"Late summer to early autumn, during rainy season\",\n \"terroir_notes\": \"Wild huitlacoche develops on maize ears infected naturally by Ustilago maydis in humid conditions. Flavor is more intense and complex than cultivated varieties, reflecting heirloom corn landraces and volcanic highland soils.\"\n },\n \"notes\": \"Best used fresh and cooked briefly to preserve its delicate earthy character. Traditional in quesadillas, tamales, soups, and sauces. Turns inky black when cooked.\"\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": 3785, "output_tokens": 900, "latency_ms": 12529.8, "usd": 0.124275, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:ingredient:huitlacoche\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"wild huitlacoche\",\n \"description\": \"Wild huitlacoche, the edible fungus Ustilago maydis that grows on ears of maize, prized in Mexican cuisine for its smoky, earthy, mushroom-like flavor and inky gray-black color.\",\n \"category\": \"fungus\",\n \"subcategory\": \"corn smut\",\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 1.5,\n \"sour\": 0.5,\n \"salty\": 0.5,\n \"bitter\": 1,\n \"umami\": 7.5\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 0.5,\n \"astringency\": 1\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"mushroom\",\n \"item\": \"fresh mushroom\",\n \"intensity\": 7\n },\n {\n \"family\": \"earth\",\n \"group\": \"soil\",\n \"item\": \"damp earth\",\n \"intensity\": 5\n },\n {\n \"family\": \"savory\",\n \"group\": \"smoke\",\n \"item\": \"woodsmoke\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"vegetal\",\n \"group\": \"corn\",\n \"item\": \"sweet corn\",\n \"qualifier\": \"cooked\",\n \"intensity\": 4\n },\n {\n \"family\": \"wood\",\n \"group\": \"forest floor\",\n \"item\": \"humus\",\n \"intensity\": 3\n }\n ],\n \"texture\": [\n \"tender\",\n \"soft\",\n \"juicy\",\n \"slightly chewy\",\n \"inky\"\n ],\n \"finish_length\": 6.5,\n \"complexity\": 7.5\n },\n \"origin\": {\n \"region\": \"Mexico (Central Highlands, esp. Estado de México, Tlaxcala, Puebla)\",\n \"season\": \"late summer to early autumn, during the maize rainy season\",\n \"terroir_notes\": \"Forms naturally on rain-fed maize ears when Ustilago maydis spores infect developing kernels; wild specimens are foraged from milpas and tend to have deeper earthy and smoky notes than cultivated versions.\"\n },\n \"notes\": \"Best used fresh and quickly, as it deteriorates within days of harvest. Traditionally sautéed with onion, garlic, epazote, and chile, then used in quesadillas, tacos, soups, and sauces.\",\n \"metadata\": {\n \"source\": \"OGS core reference dataset\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:ingredient: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": 3785, "output_tokens": 900, "latency_ms": 12341.1, "usd": 0.124275, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 3785.0, "output_tokens_mean": 941.333, "latency_ms_mean": 12607.933, "usd_sum": 0.382125 } }, { "task_id": "ogs:core:benchmark-task:struct-011", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "medium", "cuisine_region": "italian", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "6615664480900680", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing 'Barolo' as an OGS beverage. It MUST validate against the OGS beverage schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"beverage_name\": \"Barolo\",\n \"namespace\": \"core\",\n \"id_slug\": \"barolo-docg\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:barolo-docg", "ogs_version": "0.1.0", "type": "wine" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Barolo\",\n \"description\": \"A prestigious Italian red wine from the Piedmont region, made exclusively from Nebbiolo grapes. Known for its power, complexity, and aging potential.\",\n \"type\": \"wine\",\n \"subtype\": \"red still wine\",\n \"grape_varieties\": [\"Nebbiolo\"],\n \"region\": \"Piedmont, Italy\",\n \"appellation\": \"Barolo DOCG\",\n \"abv\": 14.0,\n \"residual_sugar\": 2.0,\n \"serve_temperature_c\": {\n \"min\": 16,\n \"max\": 18\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 6.5,\n \"salty\": 0,\n \"bitter\": 4.5,\n \"umami\": 3.0\n },\n \"structural\": {\n \"body\": 8.5,\n \"acidity_perception\": 7.5,\n \"tannin\": 8.5,\n \"astringency\": 7.5,\n \"alcohol_heat\": 7.0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\"family\": \"fruit\", \"group\": \"red_fruit\", \"item\": \"cherry\", \"qualifier\": \"dried\", \"intensity\": 7.0},\n {\"family\": \"fruit\", \"group\": \"red_fruit\", \"item\": \"raspberry\", \"qualifier\": \"fresh\", \"intensity\": 5.0},\n {\"family\": \"floral\", \"group\": \"flower\", \"item\": \"rose\", \"qualifier\": \"dried\", \"intensity\": 6.5},\n {\"family\": \"floral\", \"group\": \"flower\", \"item\": \"violet\", \"intensity\": 5.0},\n {\"family\": \"spice\", \"group\": \"baking_spice\", \"item\": \"clove\", \"intensity\": 4.5},\n {\"family\": \"spice\", \"group\": \"baking_spice\", \"item\": \"cinnamon\", \"intensity\": 4.0},\n {\"family\": \"earth\", \"group\": \"mineral\", \"item\": \"tar\", \"intensity\": 6.0},\n {\"family\": \"earth\", \"group\": \"fungal\", \"item\": \"truffle\", \"intensity\": 5.5},\n {\"family\": \"earth\", \"group\": \"forest\", \"item\": \"forest_floor\", \"intensity\": 5.0},\n {\"family\": \"wood\", \"group\": \"oak\", \"item\": \"cedar\", \"intensity\": 4.5},\n {\"family\": \"wood\", \"group\": \"oak\", \"item\": \"vanilla\", \"intensity\": 3.5},\n {\"family\": \"herbal\", \"group\": \"dried_herb\", \"item\": \"tobacco\", \"qualifier\": \"dried\", \"intensity\": 5.0},\n {\"family\": \"confection\", \"group\": \"cocoa\", \"item\": \"dark_chocolate\", \"intensity\": 3.5}\n ],\n \"texture\": [\"grippy\", \"firm\", \"structured\", \"velvety with age\"],\n \"finish_length\": 9.0,\n \"complexity\": 9.0\n },\n \"notes\": \"Barolo requ", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "['Nebbiolo'] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:beverage:barolo-docg", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "type": { "predicted": null, "expected": "wine", "match": false } } }, "metrics": { "input_tokens": 3758, "output_tokens": 1024, "latency_ms": 10890.6, "usd": 0.13317, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Barolo\",\n \"description\": \"A prestigious Italian red wine made exclusively from Nebbiolo grapes in the Barolo DOCG zone of Piedmont, known for its power, structure, and longevity.\",\n \"type\": \"wine\",\n \"subtype\": \"still red\",\n \"grape_varieties\": [\"Nebbiolo\"],\n \"region\": \"Piedmont\",\n \"appellation\": \"Barolo DOCG\",\n \"abv\": 14.0,\n \"residual_sugar\": 2.0,\n \"serve_temperature_c\": {\n \"min\": 16,\n \"max\": 18\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 6.5,\n \"salty\": 0,\n \"bitter\": 4.5,\n \"umami\": 2.0\n },\n \"structural\": {\n \"body\": 8.5,\n \"acidity_perception\": 7.5,\n \"tannin\": 8.5,\n \"astringency\": 7.5,\n \"alcohol_heat\": 7.0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"red_fruit\",\n \"item\": \"cherry\",\n \"qualifier\": \"dried\",\n \"intensity\": 7.0\n },\n {\n \"family\": \"fruit\",\n \"group\": \"red_fruit\",\n \"item\": \"raspberry\",\n \"qualifier\": \"fresh\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"flower\",\n \"item\": \"rose\",\n \"qualifier\": \"dried\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"floral\",\n \"group\": \"flower\",\n \"item\": \"violet\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"earth\",\n \"group\": \"forest_floor\",\n \"item\": \"truffle\",\n \"intensity\": 6.0\n },\n {\n \"family\": \"earth\",\n \"group\": \"forest_floor\",\n \"item\": \"leather\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking_spice\",\n \"item\": \"licorice\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking_spice\",\n \"item\": \"clove\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"cedar\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"dried_herb\",\n \"item\": \"tobacco\",\n \"qualifier\": \"dried\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramelized\",\n \"item\": \"tar\",\n \"intensity\": 5.5\n }\n ],\n \"texture\": [\"grippy\", \"structured\", \"firm\"],\n \"fin", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "['Nebbiolo'] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:beverage:barolo-docg", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "type": { "predicted": null, "expected": "wine", "match": false } } }, "metrics": { "input_tokens": 3758, "output_tokens": 1024, "latency_ms": 10494.5, "usd": 0.13317, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:barolo-docg\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Barolo\",\n \"description\": \"A prestigious Italian red wine from the Piedmont region, produced exclusively from Nebbiolo grapes. Known for its power, structure, and aging potential, Barolo is often called 'the king of wines and the wine of kings'.\",\n \"type\": \"wine\",\n \"subtype\": \"red still\",\n \"grape_varieties\": [\"Nebbiolo\"],\n \"region\": \"Piedmont\",\n \"appellation\": \"Barolo DOCG\",\n \"abv\": 14.0,\n \"residual_sugar\": 1.5,\n \"serve_temperature_c\": {\n \"min\": 16,\n \"max\": 18\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 0.5,\n \"sour\": 6.5,\n \"salty\": 0,\n \"bitter\": 4.0,\n \"umami\": 2.0\n },\n \"structural\": {\n \"body\": 8.0,\n \"acidity_perception\": 7.5,\n \"tannin\": 8.5,\n \"astringency\": 7.5,\n \"alcohol_heat\": 6.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\"family\": \"fruit\", \"group\": \"red_fruit\", \"item\": \"cherry\", \"qualifier\": \"dried\", \"intensity\": 7.0},\n {\"family\": \"fruit\", \"group\": \"red_fruit\", \"item\": \"raspberry\", \"intensity\": 5.0},\n {\"family\": \"floral\", \"group\": \"dried_flowers\", \"item\": \"rose\", \"qualifier\": \"dried\", \"intensity\": 6.5},\n {\"family\": \"floral\", \"group\": \"dried_flowers\", \"item\": \"violet\", \"intensity\": 5.5},\n {\"family\": \"earth\", \"group\": \"forest_floor\", \"item\": \"truffle\", \"intensity\": 6.0},\n {\"family\": \"earth\", \"group\": \"forest_floor\", \"item\": \"forest_floor\", \"intensity\": 5.5},\n {\"family\": \"spice\", \"group\": \"baking_spice\", \"item\": \"clove\", \"intensity\": 4.0},\n {\"family\": \"spice\", \"group\": \"baking_spice\", \"item\": \"anise\", \"intensity\": 3.5},\n {\"family\": \"herbal\", \"group\": \"dried_herbs\", \"item\": \"tobacco\", \"qualifier\": \"dried\", \"intensity\": 5.0},\n {\"family\": \"wood\", \"group\": \"oak\", \"item\": \"cedar\", \"intensity\": 4.5},\n {\"family\": \"savory\", \"group\": \"cured\", \"item\": \"leather\", \"intensity\": 5.0}\n ],\n \"texture\": [\"grippy\", \"structured\", \"chewy\"],\n \"finish_length\": 8.5,\n \"complexity\": 9.0\n },\n \"notes\": \"Barolo requires significant aging to soften its formidable tannins; traditional styles can benefit from 10+ years of cellaring. Pairs classically with rich meats, truffle dishes, and aged cheeses.\",", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "['Nebbiolo'] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:beverage:barolo-docg", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "type": { "predicted": null, "expected": "wine", "match": false } } }, "metrics": { "input_tokens": 3758, "output_tokens": 1024, "latency_ms": 11793.1, "usd": 0.13317, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } } ], "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": 3758.0, "output_tokens_mean": 1024.0, "latency_ms_mean": 11059.4, "usd_sum": 0.39951 } }, { "task_id": "ogs:core:benchmark-task:struct-012", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "hard", "cuisine_region": "scottish", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "bd330891a3e68b59", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing 'Islay single malt' as an OGS beverage. It MUST validate against the OGS beverage schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"beverage_name\": \"Islay single malt\",\n \"namespace\": \"core\",\n \"id_slug\": \"ardbeg-10-islay\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:ardbeg-10-islay", "ogs_version": "0.1.0", "type": "spirit" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:ardbeg-10-islay\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Islay single malt\",\n \"description\": \"A peated Islay single malt Scotch whisky with pronounced smoke, maritime character, and warming alcohol.\",\n \"type\": \"spirit\",\n \"subtype\": \"single malt Scotch whisky\",\n \"region\": \"Islay, Scotland\",\n \"abv\": 46.0,\n \"serve_temperature_c\": {\n \"min\": 18,\n \"max\": 22\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.0,\n \"sour\": 1.5,\n \"salty\": 3.5,\n \"bitter\": 4.0,\n \"umami\": 1.0\n },\n \"structural\": {\n \"body\": 7.5,\n \"acidity_perception\": 2.0,\n \"tannin\": 2.5,\n \"astringency\": 3.0,\n \"alcohol_heat\": 7.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"smoke\",\n \"item\": \"peat smoke\",\n \"intensity\": 9.0\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea\",\n \"item\": \"brine\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea\",\n \"item\": \"seaweed\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"qualifier\": \"zest\",\n \"intensity\": 4.0\n },\n {\n \"family\": \"spice\",\n \"group\": \"warm spice\",\n \"item\": \"black pepper\",\n \"intensity\": 3.5\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"toasted oak\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"vanilla\",\n \"intensity\": 3.0\n },\n {\n \"family\": \"savory\",\n \"group\": \"smoked\",\n \"item\": \"smoked meat\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"oily\",\n \"coating\",\n \"warming\"\n ],\n \"finish_length\": 9.0,\n \"complexity\": 8.5\n },\n \"notes\": \"Classic Islay profile: intense peat smoke layered with maritime salinity, citrus, and oak-driven vanilla; long, warming finish.\",\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic profile\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core: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": 3766, "output_tokens": 930, "latency_ms": 10720.5, "usd": 0.12624, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:ardbeg-10-islay\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Islay single malt\",\n \"description\": \"A peated single malt Scotch whisky from Islay, showing intense smoke, maritime character, and a long warming finish.\",\n \"type\": \"spirit\",\n \"subtype\": \"single malt whisky\",\n \"region\": \"Islay, Scotland\",\n \"abv\": 46.0,\n \"serve_temperature_c\": {\n \"min\": 18,\n \"max\": 22\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.0,\n \"sour\": 1.5,\n \"salty\": 4.0,\n \"bitter\": 3.5,\n \"umami\": 2.0\n },\n \"structural\": {\n \"body\": 7.5,\n \"acidity_perception\": 2.0,\n \"tannin\": 1.5,\n \"astringency\": 3.0,\n \"alcohol_heat\": 7.5,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\n \"family\": \"earth\",\n \"group\": \"smoke\",\n \"item\": \"peat smoke\",\n \"intensity\": 9.0\n },\n {\n \"family\": \"marine\",\n \"group\": \"sea\",\n \"item\": \"brine\",\n \"intensity\": 6.5\n },\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item\": \"kelp\",\n \"intensity\": 5.0\n },\n {\n \"family\": \"wood\",\n \"group\": \"oak\",\n \"item\": \"toasted oak\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"citrus\",\n \"item\": \"lemon\",\n \"intensity\": 4.0,\n \"qualifier\": \"zest\"\n },\n {\n \"family\": \"confection\",\n \"group\": \"sugar\",\n \"item\": \"vanilla\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"spice\",\n \"group\": \"pepper\",\n \"item\": \"black pepper\",\n \"intensity\": 4.0\n }\n ],\n \"texture\": [\n \"oily\",\n \"coating\",\n \"warming\"\n ],\n \"finish_length\": 9.0,\n \"complexity\": 8.5\n },\n \"notes\": \"Classic Islay profile: intense peat smoke, iodine, and sea spray balanced by citrus and vanilla from oak aging.\",\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic profile\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core: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": 3766, "output_tokens": 876, "latency_ms": 10424.6, "usd": 0.12219, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:beverage:ardbeg-10-islay\",\"ogs_version\":\"0.1.0\",\"primary_language\":\"en\",\"name\":\"Islay single malt\",\"description\":\"A peated Islay single malt Scotch whisky, characterised by intense smoke, maritime notes, and a long warming finish.\",\"type\":\"spirit\",\"subtype\":\"single malt whisky\",\"region\":\"Islay, Scotland\",\"abv\":46.0,\"serve_temperature_c\":{\"min\":18,\"max\":22},\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3.0,\"sour\":1.5,\"salty\":4.0,\"bitter\":4.0,\"umami\":2.0},\"structural\":{\"body\":7.5,\"acidity_perception\":2.0,\"tannin\":2.5,\"astringency\":3.0,\"alcohol_heat\":7.0,\"effervescence\":0},\"aromatics\":[{\"family\":\"earth\",\"group\":\"smoke\",\"item\":\"peat smoke\",\"intensity\":9.0},{\"family\":\"marine\",\"group\":\"sea\",\"item\":\"brine\",\"intensity\":7.0},{\"family\":\"marine\",\"group\":\"sea\",\"item\":\"seaweed\",\"intensity\":6.5},{\"family\":\"spice\",\"group\":\"medicinal\",\"item\":\"iodine\",\"intensity\":6.0},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lemon\",\"qualifier\":\"zest\",\"intensity\":4.0},{\"family\":\"wood\",\"group\":\"oak\",\"item\":\"vanilla\",\"intensity\":4.5},{\"family\":\"confection\",\"group\":\"sugar\",\"item\":\"toffee\",\"intensity\":3.5}],\"texture\":[\"oily\",\"warming\",\"coating\"],\"finish_length\":9.0,\"complexity\":8.5},\"notes\":\"Classic Islay profile: heavy peat smoke, sea spray, and medicinal phenolics balanced by oak-derived sweetness.\",\"metadata\":{\"source\":\"OGS benchmark synthetic example\",\"license\":\"CC-BY-4.0\"}}", "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": 3766, "output_tokens": 640, "latency_ms": 8433.7, "usd": 0.10449, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3766.0, "output_tokens_mean": 815.333, "latency_ms_mean": 9859.6, "usd_sum": 0.35292 } }, { "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": "{\"id\":\"ogs:core:beverage:junmai-ginjo-generic\",\"ogs_version\":\"0.1.0\",\"primary_language\":\"en\",\"name\":\"Junmai Ginjo Sake\",\"description\":\"A premium Japanese sake brewed from rice polished to at least 60%, using only rice, water, koji, and yeast, with no added distilled alcohol.\",\"type\":\"sake\",\"subtype\":\"junmai ginjo\",\"region\":\"Japan\",\"abv\":15.5,\"serve_temperature_c\":{\"min\":8,\"max\":12},\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3.5,\"sour\":3,\"salty\":0.5,\"bitter\":1.5,\"umami\":5.5},\"structural\":{\"body\":4.5,\"acidity_perception\":3,\"alcohol_heat\":4,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"orchard\",\"item\":\"pear\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"melon\",\"qualifier\":\"fresh\",\"intensity\":4},{\"family\":\"floral\",\"group\":\"white flower\",\"item\":\"jasmine\",\"intensity\":3.5},{\"family\":\"fruit\",\"group\":\"orchard\",\"item\":\"green apple\",\"qualifier\":\"fresh\",\"intensity\":3.5},{\"family\":\"confection\",\"group\":\"grain\",\"item\":\"steamed rice\",\"qualifier\":\"cooked\",\"intensity\":4.5}],\"texture\":[\"silky\",\"smooth\",\"slightly viscous\"],\"finish_length\":5.5,\"complexity\":6.5}}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:beverage:junmai-ginjo-generic", "expected": "ogs:core:beverage:junmai-ginjo-generic", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true }, "type": { "predicted": "sake", "expected": "sake", "match": true } } }, "metrics": { "input_tokens": 3773, "output_tokens": 512, "latency_ms": 7235.5, "usd": 0.094995, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\n\"id\": \"ogs:core:beverage:junmai-ginjo-generic\",\n\"ogs_version\": \"0.1.0\",\n\"primary_language\": \"en\",\n\"name\": \"Junmai Ginjo Sake\",\n\"description\": \"A premium Japanese sake brewed from rice polished to at least 60%, using only rice, water, koji, and yeast, yielding a refined aromatic profile.\",\n\"type\": \"sake\",\n\"subtype\": \"junmai-ginjo\",\n\"abv\": 15.5,\n\"serve_temperature_c\": {\n\"min\": 8,\n\"max\": 12\n},\n\"sensory_profile\": {\n\"basic_tastes\": {\n\"sweet\": 3.5,\n\"sour\": 3,\n\"salty\": 0.5,\n\"bitter\": 2,\n\"umami\": 5.5\n},\n\"structural\": {\n\"body\": 4.5,\n\"acidity_perception\": 3.5,\n\"tannin\": 0,\n\"astringency\": 1.5,\n\"alcohol_heat\": 4,\n\"effervescence\": 0\n},\n\"aromatics\": [\n{\"family\": \"fruit\", \"group\": \"orchard\", \"item\": \"pear\", \"qualifier\": \"fresh\", \"intensity\": 6},\n{\"family\": \"fruit\", \"group\": \"orchard\", \"item\": \"apple\", \"qualifier\": \"fresh\", \"intensity\": 5.5},\n{\"family\": \"fruit\", \"group\": \"tropical\", \"item\": \"melon\", \"qualifier\": \"fresh\", \"intensity\": 5},\n{\"family\": \"fruit\", \"group\": \"tropical\", \"item\": \"banana\", \"qualifier\": \"fresh\", \"intensity\": 3.5},\n{\"family\": \"floral\", \"group\": \"white-flower\", \"item\": \"white flowers\", \"intensity\": 4},\n{\"family\": \"confection\", \"group\": \"grain\", \"item\": \"steamed rice\", \"qualifier\": \"cooked\", \"intensity\": 5},\n{\"family\": \"dairy\", \"group\": \"cultured\", \"item\": \"yogurt\", \"qualifier\": \"fermented\", \"intensity\": 2}\n],\n\"texture\": [\"silky\", \"clean\", \"smooth\"],\n\"finish_length\": 6,\n\"complexity\": 6.5\n},\n\"notes\": \"Serve lightly chilled to preserve delicate ginjo-ka (fruity and floral aromas). Generic profile representative of the category.\",\n\"metadata\": {\n\"source\": \"OGS reference profile\",\n\"license\": \"CC-BY-4.0\"\n}\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core: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": 3773, "output_tokens": 785, "latency_ms": 9886.7, "usd": 0.11547, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:beverage:junmai-ginjo-generic\",\"ogs_version\":\"0.1.0\",\"name\":\"Junmai Ginjo Sake\",\"type\":\"sake\",\"subtype\":\"junmai ginjo\",\"abv\":15.5,\"serve_temperature_c\":{\"min\":8,\"max\":12},\"sensory_profile\":{\"basic_tastes\":{\"sweet\":3.5,\"sour\":3,\"salty\":0.5,\"bitter\":2,\"umami\":4.5},\"structural\":{\"body\":4,\"acidity_perception\":3,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":3.5,\"effervescence\":0},\"aromatics\":[{\"family\":\"fruit\",\"group\":\"orchard\",\"item\":\"pear\",\"intensity\":5.5},{\"family\":\"fruit\",\"group\":\"tropical\",\"item\":\"melon\",\"intensity\":4.5},{\"family\":\"floral\",\"group\":\"white-flower\",\"item\":\"jasmine\",\"intensity\":3.5},{\"family\":\"confection\",\"group\":\"grain\",\"item\":\"steamed rice\",\"intensity\":4}],\"texture\":[\"silky\",\"smooth\"],\"finish_length\":5.5,\"complexity\":6}}", "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": 3773, "output_tokens": 378, "latency_ms": 5127.1, "usd": 0.084945, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3773.0, "output_tokens_mean": 558.333, "latency_ms_mean": 7416.433, "usd_sum": 0.29541 } }, { "task_id": "ogs:core:benchmark-task:struct-014", "category": "structured_output", "capability": "schema_valid_beverage", "difficulty": "easy", "cuisine_region": "german", "scorer": "schema_validation", "context_needs": [ "schema.beverage", "vocab.beverage_types", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "3fe3fe74f8d80260", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS beverage schema (`schema/beverage.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/beverage.schema.json\",\n \"title\": \"OGS Beverage\",\n \"description\": \"A beverage entity with type, structural attributes, sensory profile, and provenance.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"type\",\n \"sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"wine\",\n \"beer\",\n \"spirit\",\n \"cider\",\n \"sake\",\n \"other\"\n ]\n },\n \"subtype\": {\n \"type\": \"string\"\n },\n \"grape_varieties\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"vintage\": {\n \"type\": \"integer\"\n },\n \"region\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"appellation\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"producer\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"abv\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"residual_sugar\": {\n \"type\": \"number\",\n \"minimum\": 0\n },\n \"serve_temperature_c\": {\n \"type\": \"object\",\n \"properties\": {\n \"min\": {\n \"type\": \"number\"\n },\n \"max\": {\n \"type\": \"number\"\n }\n },\n \"additionalProperties\": false,\n \"description\": \"Recommended serving temperature range in degrees Celsius (SI canonical).\"\n },\n \"sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Beverage types\n\nwine, beer, spirit, cider, sake, other\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce a JSON document describing 'Oktoberfest Märzen lager' as an OGS beverage. It MUST validate against the OGS beverage schema. Respond with ONLY the JSON object.\n\nINPUT:\n{\n \"beverage_name\": \"Oktoberfest Märzen lager\",\n \"namespace\": \"core\",\n \"id_slug\": \"oktoberfest-marzen\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/beverage.schema.json", "required_fields": { "id": "ogs:core:beverage:oktoberfest-marzen", "ogs_version": "0.1.0", "type": "beer" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"description\": \"A traditional amber German lager brewed in the Märzen style, malt-forward with toasty, bready character and a clean, dry finish.\",\n \"type\": \"beer\",\n \"subtype\": \"märzen\",\n \"region\": \"Bavaria\",\n \"abv\": 5.8,\n \"serve_temperature_c\": {\n \"min\": 7,\n \"max\": 9\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 1\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 3,\n \"effervescence\": 5\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"caramel\",\n \"intensity\": 5\n },\n {\n \"family\": \"confection\",\n \"group\": \"baked\",\n \"item\": \"toasted bread\",\n \"intensity\": 6\n },\n {\n \"family\": \"confection\",\n \"group\": \"baked\",\n \"item\": \"biscuit\",\n \"intensity\": 4.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"dried\",\n \"item\": \"raisin\",\n \"qualifier\": \"dried\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"hops\",\n \"item\": \"noble hops\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"group\": \"nut\",\n \"item\": \"hazelnut\",\n \"intensity\": 2\n }\n ],\n \"texture\": [\n \"smooth\",\n \"rounded\",\n \"crisp finish\"\n ],\n \"finish_length\": 5.5,\n \"complexity\": 5\n },\n \"notes\": \"Classic Oktoberfest-style lager: amber color, malt-driven aroma of toasted bread and caramel, restrained hop bitterness, and a clean lager finish.\",\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic profile\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core: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": 3780, "output_tokens": 823, "latency_ms": 9339.5, "usd": 0.118425, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"description\": \"A traditional amber German lager brewed in the Märzen style, malt-forward with toasty notes and a clean, crisp finish. Historically brewed in March and served at Oktoberfest.\",\n \"type\": \"beer\",\n \"subtype\": \"märzen\",\n \"region\": \"Bavaria\",\n \"appellation\": \"Munich\",\n \"abv\": 5.8,\n \"serve_temperature_c\": {\n \"min\": 7,\n \"max\": 9\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 1.5\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 3,\n \"effervescence\": 6\n },\n \"aromatics\": [\n {\n \"family\": \"fruit\",\n \"group\": \"dried_fruit\",\n \"item\": \"raisin\",\n \"qualifier\": \"dried\",\n \"intensity\": 2.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"caramel\",\n \"intensity\": 5.5\n },\n {\n \"family\": \"confection\",\n \"group\": \"toasted\",\n \"item\": \"toasted bread\",\n \"qualifier\": \"cooked\",\n \"intensity\": 5\n },\n {\n \"family\": \"herbal\",\n \"group\": \"hops\",\n \"item\": \"noble hops\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking_spice\",\n \"item\": \"nutmeg\",\n \"intensity\": 1.5\n }\n ],\n \"texture\": [\n \"smooth\",\n \"medium-bodied\",\n \"crisp\"\n ],\n \"finish_length\": 6,\n \"complexity\": 6\n },\n \"notes\": \"Classic Oktoberfest Märzen: rich malt character with biscuit and caramel aromas, balanced by noble hop bitterness and a dry, clean lager finish.\",\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic sample\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core: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": 3780, "output_tokens": 833, "latency_ms": 11296.3, "usd": 0.119175, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:beverage:oktoberfest-marzen\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Oktoberfest Märzen lager\",\n \"description\": \"A traditional German amber lager brewed in the Märzen style, featuring rich malt character, toasted bread crust notes, and a clean, dry finish. Historically brewed in March and served at Oktoberfest.\",\n \"type\": \"beer\",\n \"subtype\": \"märzen\",\n \"region\": \"Bavaria\",\n \"abv\": 5.8,\n \"serve_temperature_c\": {\n \"min\": 7,\n \"max\": 10\n },\n \"sensory_profile\": {\n \"basic_tastes\": {\n \"sweet\": 3.5,\n \"sour\": 1,\n \"salty\": 0,\n \"bitter\": 3,\n \"umami\": 1.5\n },\n \"structural\": {\n \"body\": 6,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 2.5,\n \"effervescence\": 5.5\n },\n \"aromatics\": [\n {\n \"family\": \"confection\",\n \"group\": \"caramel\",\n \"item\": \"caramel\",\n \"intensity\": 5\n },\n {\n \"family\": \"confection\",\n \"group\": \"baked\",\n \"item\": \"toasted bread crust\",\n \"intensity\": 6\n },\n {\n \"family\": \"herbal\",\n \"group\": \"hop\",\n \"item\": \"noble hops\",\n \"intensity\": 3\n },\n {\n \"family\": \"spice\",\n \"group\": \"baking spice\",\n \"item\": \"clove\",\n \"intensity\": 1.5\n },\n {\n \"family\": \"fruit\",\n \"group\": \"orchard\",\n \"item\": \"apple\",\n \"qualifier\": \"dried\",\n \"intensity\": 2\n },\n {\n \"family\": \"earth\",\n \"group\": \"grain\",\n \"item\": \"malted barley\",\n \"intensity\": 6.5\n }\n ],\n \"texture\": [\n \"smooth\",\n \"round\",\n \"medium-bodied\"\n ],\n \"finish_length\": 5.5,\n \"complexity\": 5\n },\n \"notes\": \"Best enjoyed fresh in autumn; pairs traditionally with roasted meats, pretzels, and sausages.\",\n \"metadata\": {\n \"source\": \"OGS benchmark synthetic example\",\n \"license\": \"CC-BY-4.0\"\n }\n}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core: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": 3780, "output_tokens": 835, "latency_ms": 10585.8, "usd": 0.119325, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 3780.0, "output_tokens_mean": 830.333, "latency_ms_mean": 10407.2, "usd_sum": 0.356925 } }, { "task_id": "ogs:core:benchmark-task:struct-015", "category": "structured_output", "capability": "schema_valid_pairing", "difficulty": "hard", "cuisine_region": "french", "scorer": "schema_validation", "context_needs": [ "schema.pairing", "vocab.match_types", "vocab.explanation_codes", "vocab.grade_scale", "id.format", "ogs_version" ], "prompt_template_hash": "f0c01fa20f35eb51", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS pairing schema (`schema/pairing.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/pairing.schema.json\",\n \"title\": \"OGS Pairing\",\n \"description\": \"A scored, explained pairing between a dish and a beverage.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"dish_ref\",\n \"beverage_ref\",\n \"match_types\",\n \"overall_score\",\n \"grade\",\n \"explanation_codes\",\n \"confidence\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:pairing:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"dish_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"beverage_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"match_types\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/match_type_entry\"\n }\n },\n \"overall_score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"grade\": {\n \"type\": \"string\",\n \"enum\": [\n \"A+\",\n \"A\",\n \"B+\",\n \"B\",\n \"C+\",\n \"C\",\n \"D\",\n \"F\"\n ]\n },\n \"explanation_codes\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/explanation_code_entry\"\n }\n },\n \"risks\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/risk_entry\"\n }\n },\n \"confidence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"evidence\": {\n \"$ref\": \"#/$defs/evidence\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"match_type_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"type\",\n \"score\"\n ],\n \"properties\": {\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"harmony\",\n \"contrast\",\n \"bridge\",\n \"intensity_alignment\",\n \"structural_balance\",\n \"refresh\"\n ]\n },\n \"score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"primary\": {\n \"type\": \"boolean\"\n }\n },\n \"additionalProperties\": false\n },\n \"explanation_code_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"weight\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"detail\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"risk_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\",\n \"severity\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"severity\": {\n \"type\": \"string\",\n \"enum\": [\n \"low\",\n \"medium\",\n \"high\"\n ]\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"mitigation\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"evidence\": {\n \"type\": \"object\",\n \"properties\": {\n \"method\": {\n \"type\": \"string\",\n \"enum\": [\n \"expert_panel\",\n \"instrumental\",\n \"computed\",\n \"estimated\"\n ]\n },\n \"sources\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n### OGS Explanation Codes\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS pairing JSON document for the described match. It MUST validate against the OGS pairing schema. Respond with ONLY the JSON.\n\nINPUT:\n{\n \"pairing_slug\": \"crottin-sancerre\",\n \"dish_ref\": \"ogs:core:dish:crottin-de-chavignol\",\n \"beverage_ref\": \"ogs:core:beverage:sancerre-blanc\",\n \"intent\": \"Classic Loire regional pairing: Sancerre's acidity and citrus meet fresh goat cheese's tang.\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/pairing.schema.json", "required_fields": { "id": "ogs:core:pairing:crottin-sancerre", "ogs_version": "0.1.0", "dish_ref": "ogs:core:dish:crottin-de-chavignol", "beverage_ref": "ogs:core:beverage:sancerre-blanc" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Crottin de Chavignol with Sancerre Blanc\",\n \"description\": \"Classic Loire regional pairing: Sancerre's acidity and citrus meet fresh goat cheese's tang.\",\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\": \"Iconic Loire regional affinity between Chavignol goat cheese and Sancerre.\",\n \"primary\": true\n },\n {\n \"type\": \"refresh\",\n \"score\": 90,\n \"description\": \"Sancerre's bright acidity refreshes the palate against the creamy, tangy cheese.\"\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 88\n }\n ],\n \"overall_score\": 95,\n \"grade\": \"A+\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.35,\n \"detail\": \"Chavignol and Sancerre are produced in neighboring Loire villages, a textbook terroir pairing.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.3,\n \"detail\": \"Sancerre's crisp acidity cuts through the cheese's lactic richness.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.2,\n \"detail\": \"The wine's acidity mirrors and balances the tangy, lactic acidity of the fresh goat cheese.\"\n },\n {\n \"code\": \"AROMA_SHARED_HERBAL\",\n \"weight\": 0.15,\n \"detail\": \"Sauvignon Blanc's green herbal and citrus notes echo the fresh, grassy character of the goat cheese.\"\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_INTENSITY_MISMATCH\",\n \"severity\": \"low\",\n \"description\": \"A very aged, dry crottin could slightly outpace a light Sancerre.\",\n \"mitigation\": \"Choose a younger, fresher crottin or a more structured Sancerre for aged cheese.\"\n }\n ],\n \"confidence\": 0.95,\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"notes\": \"Widely recognized as a benchmark French regional pairing.\"\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": 5481, "output_tokens": 884, "latency_ms": 10906.8, "usd": 0.148515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:pairing:crottin-sancerre\",\"ogs_version\":\"0.1.0\",\"name\":\"Crottin de Chavignol with Sancerre Blanc\",\"description\":\"Classic Loire regional pairing: Sancerre's acidity and citrus meet fresh goat cheese's tang.\",\"dish_ref\":\"ogs:core:dish:crottin-de-chavignol\",\"beverage_ref\":\"ogs:core:beverage:sancerre-blanc\",\"match_types\":[{\"type\":\"harmony\",\"score\":94,\"primary\":true,\"description\":\"Regional Loire affinity between Sancerre and Crottin de Chavignol.\"},{\"type\":\"refresh\",\"score\":90,\"description\":\"High acidity refreshes the palate against the creamy tang of goat cheese.\"},{\"type\":\"structural_balance\",\"score\":88,\"description\":\"Acidity balances the richness and lactic tang of the cheese.\"}],\"overall_score\":93,\"grade\":\"A\",\"explanation_codes\":[{\"code\":\"HARMONY_REGIONAL\",\"weight\":0.3,\"detail\":\"Both originate from the Loire Valley, a textbook terroir pairing.\"},{\"code\":\"REFRESH_ACID\",\"weight\":0.25,\"detail\":\"Sancerre's bright acidity cleanses the palate between bites of creamy goat cheese.\"},{\"code\":\"STRUCT_ACIDITY_BALANCE\",\"weight\":0.2,\"detail\":\"The wine's acidity matches and balances the lactic tang of the crottin.\"},{\"code\":\"AROMA_SHARED_HERBAL\",\"weight\":0.15,\"detail\":\"Shared grassy, herbal notes link Sauvignon Blanc with fresh goat cheese.\"},{\"code\":\"STRUCT_INTENSITY_MATCH\",\"weight\":0.1,\"detail\":\"Both partners are medium-light in intensity, neither overpowers the other.\"}],\"risks\":[{\"code\":\"RISK_ACID_CLASH\",\"severity\":\"low\",\"description\":\"Very young, sharp cheese paired with very high-acid Sancerre could feel overly sharp.\",\"mitigation\":\"Choose a slightly aged crottin (demi-sec) to soften the acid interplay.\"}],\"confidence\":0.92,\"evidence\":{\"method\":\"expert_panel\",\"notes\":\"Canonical Loire Valley pairing widely endorsed by sommeliers.\"}}", "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": 5481, "output_tokens": 787, "latency_ms": 11913.8, "usd": 0.14124, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:pairing:crottin-sancerre\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Crottin de Chavignol with Sancerre Blanc\",\n \"description\": \"Classic Loire regional pairing: Sancerre's crisp acidity and citrus notes meet the tangy freshness of goat cheese.\",\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\": 94,\n \"primary\": true,\n \"description\": \"Regional Loire affinity between Chavignol goat cheese and Sancerre.\"\n },\n {\n \"type\": \"refresh\",\n \"score\": 90,\n \"description\": \"Sancerre's acidity refreshes the palate against the cheese's creamy tang.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 88,\n \"description\": \"Acidity balances the richness and lactic tang of fresh goat cheese.\"\n }\n ],\n \"overall_score\": 93,\n \"grade\": \"A\",\n \"explanation_codes\": [\n {\n \"code\": \"HARMONY_REGIONAL\",\n \"weight\": 0.35,\n \"detail\": \"Both hail from the Loire Valley, a textbook terroir pairing.\"\n },\n {\n \"code\": \"STRUCT_ACIDITY_BALANCE\",\n \"weight\": 0.3,\n \"detail\": \"Sancerre's bright acidity matches the lactic acidity of the goat cheese.\"\n },\n {\n \"code\": \"REFRESH_ACID\",\n \"weight\": 0.2,\n \"detail\": \"High acidity cleanses the palate between bites of creamy cheese.\"\n },\n {\n \"code\": \"AROMA_SHARED_HERBAL\",\n \"weight\": 0.15,\n \"detail\": \"Grassy, herbal notes appear in both the cheese and Sauvignon Blanc.\"\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_INTENSITY_MISMATCH\",\n \"severity\": \"low\",\n \"description\": \"Very aged, pungent Crottin could slightly overshadow a lean Sancerre.\",\n \"mitigation\": \"Serve a younger Crottin or choose a riper vintage Sancerre.\"\n }\n ],\n \"confidence\": 0.92,\n \"evidence\": {\n \"method\": \"expert_panel\",\n \"notes\": \"Canonical Loire regional pairing widely documented in sommelier literature.\"\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": 5481, "output_tokens": 883, "latency_ms": 11786.7, "usd": 0.14844, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 5481.0, "output_tokens_mean": 851.333, "latency_ms_mean": 11535.767, "usd_sum": 0.438195 } }, { "task_id": "ogs:core:benchmark-task:struct-016", "category": "structured_output", "capability": "schema_valid_dish", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "schema_validation", "context_needs": [ "schema.dish", "vocab.component_roles", "vocab.cooking_methods", "vocab.courses", "vocab.service_temperatures", "vocab.aromatic_families", "scales.basic_tastes", "scales.structural", "id.format", "ogs_version" ], "prompt_template_hash": "284b25ae8f0dc3ef", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS dish schema (`schema/dish.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/dish.schema.json\",\n \"title\": \"OGS Dish\",\n \"description\": \"A composed dish with components, cooking methods, and overall sensory profile.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"components\",\n \"overall_sensory_profile\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"cuisine\": {\n \"type\": \"string\",\n \"description\": \"Free-text cuisine name (v0.1) OR a cuisine entity reference matching ogs::cuisine: (v0.2+).\"\n },\n \"course\": {\n \"type\": \"string\",\n \"enum\": [\n \"amuse\",\n \"appetizer\",\n \"soup\",\n \"salad\",\n \"fish\",\n \"main\",\n \"cheese\",\n \"dessert\",\n \"petit_four\"\n ]\n },\n \"service_temperature\": {\n \"type\": \"string\",\n \"enum\": [\n \"frozen\",\n \"cold\",\n \"cool\",\n \"room\",\n \"warm\",\n \"hot\",\n \"very_hot\"\n ]\n },\n \"components\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/component\"\n }\n },\n \"overall_sensory_profile\": {\n \"$ref\": \"#/$defs/sensory_profile\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"component\": {\n \"type\": \"object\",\n \"required\": [\n \"role\",\n \"ingredient_ref\"\n ],\n \"properties\": {\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"main_protein\",\n \"main_vegetable\",\n \"starch\",\n \"sauce\",\n \"fat_component\",\n \"acid_component\",\n \"aromatic_garnish\",\n \"seasoning\",\n \"textural_element\"\n ]\n },\n \"ingredient_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:ingredient:[a-z0-9-]+$\"\n },\n \"cooking_method\": {\n \"type\": \"string\",\n \"enum\": [\n \"raw\",\n \"seared\",\n \"grilled\",\n \"roasted\",\n \"braised\",\n \"poached\",\n \"steamed\",\n \"fried\",\n \"confit\",\n \"smoked\",\n \"fermented\",\n \"cured\",\n \"pickled\",\n \"dehydrated\",\n \"sous_vide\",\n \"blanched\",\n \"sauteed\",\n \"baked\",\n \"charred\",\n \"emulsified\"\n ]\n },\n \"maillard_index\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"reduction_level\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 5\n },\n \"proportion\": {\n \"type\": \"string\",\n \"enum\": [\n \"dominant\",\n \"significant\",\n \"accent\",\n \"trace\"\n ]\n },\n \"sensory_contribution\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"additionalProperties\": true\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"sensory_profile\": {\n \"type\": \"object\",\n \"properties\": {\n \"basic_tastes\": {\n \"$ref\": \"#/$defs/basic_tastes\"\n },\n \"structural\": {\n \"$ref\": \"#/$defs/structural\"\n },\n \"aromatics\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/aromatic_entry\"\n }\n },\n \"texture\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"finish_length\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"complexity\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n }\n },\n \"additionalProperties\": true\n },\n \"basic_tastes\": {\n \"type\": \"object\",\n \"properties\": {\n \"sweet\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"sour\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"salty\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"bitter\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"umami\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"structural\": {\n \"type\": \"object\",\n \"properties\": {\n \"body\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"acidity_perception\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"tannin\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"astringency\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"alcohol_heat\": {\n \"$ref\": \"#/$defs/intensity_value\"\n },\n \"effervescence\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"intensity_value\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"aromatic_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"family\",\n \"group\",\n \"item\",\n \"intensity\"\n ],\n \"properties\": {\n \"family\": {\n \"type\": \"string\",\n \"enum\": [\n \"fruit\",\n \"floral\",\n \"herbal\",\n \"spice\",\n \"earth\",\n \"wood\",\n \"dairy\",\n \"savory\",\n \"confection\",\n \"vegetal\",\n \"marine\"\n ]\n },\n \"group\": {\n \"type\": \"string\"\n },\n \"item\": {\n \"type\": \"string\"\n },\n \"qualifier\": {\n \"type\": \"string\",\n \"enum\": [\n \"fresh\",\n \"dried\",\n \"cooked\",\n \"candied\",\n \"fermented\",\n \"zest\",\n \"overripe\"\n ]\n },\n \"intensity\": {\n \"$ref\": \"#/$defs/intensity_value\"\n }\n },\n \"additionalProperties\": false\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Component roles\n\nmain_protein, main_vegetable, starch, sauce, fat_component, acid_component, aromatic_garnish, seasoning, textural_element\n\n### Cooking methods\n\nraw, seared, grilled, roasted, braised, poached, steamed, fried, confit, smoked, fermented, cured, pickled, dehydrated, sous_vide, blanched, sauteed, baked, charred, emulsified\n\n### Dish courses\n\namuse, appetizer, soup, salad, fish, main, cheese, dessert, petit_four\n\n### Service temperatures\n\nfrozen, cold, cool, room, warm, hot, very_hot\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS dish JSON for tonkotsu ramen (pork-bone broth, wheat noodles, chashu, soft egg, nori, scallion). Respond with ONLY the JSON.\n\nINPUT:\n{\n \"dish_name\": \"tonkotsu ramen\",\n \"namespace\": \"core\",\n \"id_slug\": \"tonkotsu-ramen\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/dish.schema.json", "required_fields": { "id": "ogs:core:dish:tonkotsu-ramen", "ogs_version": "0.1.0", "course": "main" } }, "samples": [ { "sample": 0, "raw_response": "{\n\"id\": \"ogs:core:dish:tonkotsu-ramen\",\n\"ogs_version\": \"0.1.0\",\n\"primary_language\": \"en\",\n\"name\": \"Tonkotsu Ramen\",\n\"description\": \"Rich pork-bone broth with wheat noodles, chashu pork, soft-boiled egg, nori, and scallion.\",\n\"cuisine\": \"ogs:core:cuisine:japanese\",\n\"course\": \"main\",\n\"service_temperature\": \"very_hot\",\n\"components\": [\n{\n\"role\": \"sauce\",\n\"ingredient_ref\": \"ogs:core:ingredient:tonkotsu-broth\",\n\"cooking_method\": \"braised\",\n\"proportion\": \"dominant\",\n\"sensory_contribution\": {\n\"basic_tastes\": {\"salty\": 7, \"umami\": 9, \"sweet\": 2, \"sour\": 0, \"bitter\": 1},\n\"aromatics\": [\n{\"family\": \"savory\", \"group\": \"meaty\", \"item\": \"pork\", \"qualifier\": \"cooked\", \"intensity\": 9},\n{\"family\": \"savory\", \"group\": \"broth\", \"item\": \"collagen\", \"intensity\": 7}\n],\n\"texture\": [\"creamy\", \"unctuous\"]\n}\n},\n{\n\"role\": \"starch\",\n\"ingredient_ref\": \"ogs:core:ingredient:wheat-ramen-noodles\",\n\"cooking_method\": \"blanched\",\n\"proportion\": \"significant\",\n\"sensory_contribution\": {\n\"basic_tastes\": {\"salty\": 2, \"umami\": 2, \"sweet\": 1, \"sour\": 0, \"bitter\": 0},\n\"texture\": [\"springy\", \"chewy\"]\n}\n},\n{\n\"role\": \"main_protein\",\n\"ingredient_ref\": \"ogs:core:ingredient:chashu-pork\",\n\"cooking_method\": \"braised\",\n\"maillard_index\": 3,\n\"proportion\": \"significant\",\n\"sensory_contribution\": {\n\"basic_tastes\": {\"salty\": 6, \"umami\": 8, \"sweet\": 3, \"sour\": 0, \"bitter\": 0},\n\"aromatics\": [\n{\"family\": \"savory\", \"group\": \"meaty\", \"item\": \"roasted pork\", \"qualifier\": \"cooked\", \"intensity\": 8},\n{\"family\": \"savory\", \"group\": \"soy\", \"item\": \"soy sauce\", \"intensity\": 5}\n],\n\"texture\": [\"tender\", \"melting\"]\n}\n},\n{\n\"role\": \"main_protein\",\n\"ingredient_ref\": \"ogs:core:ingredient:ajitama-egg\",\n\"cooking_method\": \"poached\",\n\"proportion\": \"accent\",\n\"sensory_contribution\": {\n\"basic_tastes\": {\"salty\": 5, \"umami\": 6, \"sweet\": 2, \"sour\": 0, \"bitter\": 0},\n\"aromatics\": [\n{\"family\": \"savory\", \"group\": \"egg\", \"item\": \"yolk\", \"qualifier\": \"cooked\", \"intensity\": 6}\n],\n\"texture\": [\"jammy\", \"creamy\"]\n}\n},\n{\n\"role\": \"textural_element\",\n\"ingredient_ref\": \"ogs:core:ingredient:nori\",\n\"cooking_method\": \"d", "compliant": false, "score": 0.0, "detail": { "error": "no_json" }, "metrics": { "input_tokens": 4578, "output_tokens": 1024, "latency_ms": 10171.7, "usd": 0.14547, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 1, "raw_response": "{\n\"id\": \"ogs:core:dish:tonkotsu-ramen\",\n\"ogs_version\": \"0.1.0\",\n\"primary_language\": \"en\",\n\"name\": \"Tonkotsu Ramen\",\n\"description\": \"Rich pork-bone broth with wheat noodles, chashu pork, soft-boiled egg, nori, and scallions.\",\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\"sensory_contribution\": {\n\"basic_tastes\": {\"sweet\": 2, \"sour\": 0.5, \"salty\": 7, \"bitter\": 1, \"umami\": 9},\n\"aromatics\": [\n{\"family\": \"savory\", \"group\": \"meaty\", \"item\": \"pork\", \"qualifier\": \"cooked\", \"intensity\": 8.5},\n{\"family\": \"savory\", \"group\": \"broth\", \"item\": \"bone_marrow\", \"qualifier\": \"cooked\", \"intensity\": 7}\n],\n\"texture\": [\"creamy\", \"unctuous\"]\n}\n},\n{\n\"role\": \"starch\",\n\"ingredient_ref\": \"ogs:core:ingredient:wheat-noodles\",\n\"cooking_method\": \"poached\",\n\"proportion\": \"significant\",\n\"sensory_contribution\": {\n\"basic_tastes\": {\"sweet\": 1, \"sour\": 0, \"salty\": 2, \"bitter\": 0, \"umami\": 2},\n\"texture\": [\"chewy\", \"springy\"]\n}\n},\n{\n\"role\": \"main_protein\",\n\"ingredient_ref\": \"ogs:core:ingredient:chashu-pork\",\n\"cooking_method\": \"braised\",\n\"maillard_index\": 3,\n\"proportion\": \"significant\",\n\"sensory_contribution\": {\n\"basic_tastes\": {\"sweet\": 3, \"sour\": 0, \"salty\": 6, \"bitter\": 0.5, \"umami\": 8},\n\"aromatics\": [\n{\"family\": \"savory\", \"group\": \"meaty\", \"item\": \"pork\", \"qualifier\": \"cooked\", \"intensity\": 8},\n{\"family\": \"savory\", \"group\": \"caramelized\", \"item\": \"soy\", \"qualifier\": \"cooked\", \"intensity\": 6}\n],\n\"texture\": [\"tender\", \"fatty\"]\n}\n},\n{\n\"role\": \"main_protein\",\n\"ingredient_ref\": \"ogs:core:ingredient:ajitsuke-tamago\",\n\"cooking_method\": \"poached\",\n\"proportion\": \"accent\",\n\"sensory_contribution\": {\n\"basic_tastes\": {\"sweet\": 2.5, \"sour\": 0.5, \"salty\": 5, \"bitter\": 0, \"umami\": 6},\n\"aromatics\": [\n{\"family\": \"savory\", \"group\": \"egg\", \"item\": \"yolk\", \"qualifier\": \"cooked\", \"intensity\": 6}\n],\n\"texture\": [\"jammy\", \"creamy\"]\n}\n},\n{\n\"role\": \"textural_element\",\n\"ingredient_ref\": \"ogs:core:", "compliant": false, "score": 0.0, "detail": { "error": "no_json" }, "metrics": { "input_tokens": 4578, "output_tokens": 1024, "latency_ms": 10155.1, "usd": 0.14547, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 2, "raw_response": "{\n \"id\": \"ogs:core:dish:tonkotsu-ramen\",\n \"ogs_version\": \"0.1.0\",\n \"primary_language\": \"en\",\n \"name\": \"Tonkotsu Ramen\",\n \"description\": \"Rich pork-bone broth with wheat noodles, chashu pork, soft-boiled egg, nori, and scallion.\",\n \"cuisine\": \"Japanese\",\n \"course\": \"main\",\n \"service_temperature\": \"very_hot\",\n \"components\": [\n {\n \"role\": \"sauce\",\n \"ingredient_ref\": \"ogs:core:ingredient:tonkotsu-broth\",\n \"cooking_method\": \"braised\",\n \"proportion\": \"dominant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 7.5,\n \"umami\": 9,\n \"sweet\": 2\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork\",\n \"qualifier\": \"cooked\",\n \"intensity\": 8.5\n }\n ],\n \"texture\": [\"creamy\", \"unctuous\"]\n }\n },\n {\n \"role\": \"starch\",\n \"ingredient_ref\": \"ogs:core:ingredient:wheat-ramen-noodles\",\n \"cooking_method\": \"blanched\",\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 2\n },\n \"texture\": [\"chewy\", \"springy\"]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:chashu-pork\",\n \"cooking_method\": \"braised\",\n \"maillard_index\": 3,\n \"proportion\": \"significant\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 6,\n \"sweet\": 3,\n \"umami\": 8\n },\n \"aromatics\": [\n {\n \"family\": \"savory\",\n \"group\": \"meaty\",\n \"item\": \"pork belly\",\n \"qualifier\": \"cooked\",\n \"intensity\": 7\n }\n ],\n \"texture\": [\"tender\", \"melting\"]\n }\n },\n {\n \"role\": \"main_protein\",\n \"ingredient_ref\": \"ogs:core:ingredient:soft-boiled-egg\",\n \"cooking_method\": \"poached\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 4,\n \"umami\": 5\n },\n \"texture\": [\"jammy\", \"custardy\"]\n }\n },\n {\n \"role\": \"textural_element\",\n \"ingredient_ref\": \"ogs:core:ingredient:nori\",\n \"cooking_method\": \"dehydrated\",\n \"proportion\": \"accent\",\n \"sensory_contribution\": {\n \"basic_tastes\": {\n \"salty\": 4,\n \"umami\": 6\n },\n \"aromatics\": [\n {\n \"family\": \"marine\",\n \"group\": \"seaweed\",\n \"item", "compliant": false, "score": 0.0, "detail": { "error": "no_json" }, "metrics": { "input_tokens": 4578, "output_tokens": 1024, "latency_ms": 10128.8, "usd": 0.14547, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } } ], "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": 0.0, "metrics": { "input_tokens_mean": 4578.0, "output_tokens_mean": 1024.0, "latency_ms_mean": 10151.867, "usd_sum": 0.43641 } }, { "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": "{\"id\":\"ogs:core:dish:pico-de-gallo\",\"ogs_version\":\"0.1.0\",\"name\":\"Pico de Gallo\",\"cuisine\":\"Mexican\",\"course\":\"appetizer\",\"service_temperature\":\"cool\",\"components\":[{\"role\":\"main_vegetable\",\"ingredient_ref\":\"ogs:core:ingredient:tomato\",\"cooking_method\":\"raw\",\"proportion\":\"dominant\"},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:onion\",\"cooking_method\":\"raw\",\"proportion\":\"significant\"},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:cilantro\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"seasoning\",\"ingredient_ref\":\"ogs:core:ingredient:jalapeno\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"acid_component\",\"ingredient_ref\":\"ogs:core:ingredient:lime\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"seasoning\",\"ingredient_ref\":\"ogs:core:ingredient:salt\",\"proportion\":\"trace\"}],\"overall_sensory_profile\":{\"basic_tastes\":{\"sweet\":2.5,\"sour\":6,\"salty\":4,\"bitter\":1,\"umami\":3.5},\"structural\":{\"body\":3,\"acidity_perception\":7},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"onion\",\"qualifier\":\"fresh\",\"intensity\":6},{\"family\":\"herbal\",\"group\":\"fresh_herb\",\"item\":\"cilantro\",\"qualifier\":\"fresh\",\"intensity\":6.5},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lime\",\"qualifier\":\"zest\",\"intensity\":6},{\"family\":\"vegetal\",\"group\":\"nightshade\",\"item\":\"tomato\",\"qualifier\":\"fresh\",\"intensity\":5.5},{\"family\":\"spice\",\"group\":\"chili\",\"item\":\"jalapeno\",\"qualifier\":\"fresh\",\"intensity\":5}],\"texture\":[\"crunchy\",\"juicy\",\"chunky\"],\"finish_length\":4,\"complexity\":5.5}}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:pico-de-gallo", "expected": "ogs:core:dish:pico-de-gallo", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 4552, "output_tokens": 728, "latency_ms": 9002.5, "usd": 0.12288, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:dish:pico-de-gallo\",\"ogs_version\":\"0.1.0\",\"name\":\"Pico de Gallo\",\"cuisine\":\"Mexican\",\"course\":\"appetizer\",\"service_temperature\":\"cool\",\"components\":[{\"role\":\"main_vegetable\",\"ingredient_ref\":\"ogs:core:ingredient:tomato\",\"cooking_method\":\"raw\",\"proportion\":\"dominant\"},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:onion\",\"cooking_method\":\"raw\",\"proportion\":\"significant\"},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:cilantro\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"seasoning\",\"ingredient_ref\":\"ogs:core:ingredient:jalapeno\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"acid_component\",\"ingredient_ref\":\"ogs:core:ingredient:lime\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"seasoning\",\"ingredient_ref\":\"ogs:core:ingredient:salt\",\"proportion\":\"trace\"}],\"overall_sensory_profile\":{\"basic_tastes\":{\"sweet\":2,\"sour\":6,\"salty\":4,\"bitter\":1,\"umami\":3},\"structural\":{\"body\":3,\"acidity_perception\":7},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"fresh_vegetable\",\"item\":\"tomato\",\"qualifier\":\"fresh\",\"intensity\":6},{\"family\":\"herbal\",\"group\":\"fresh_herb\",\"item\":\"cilantro\",\"qualifier\":\"fresh\",\"intensity\":6},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lime\",\"qualifier\":\"fresh\",\"intensity\":6},{\"family\":\"spice\",\"group\":\"chili\",\"item\":\"jalapeno\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"onion\",\"qualifier\":\"fresh\",\"intensity\":5}],\"texture\":[\"crunchy\",\"juicy\",\"chunky\"],\"finish_length\":4,\"complexity\":6}}", "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": 4552, "output_tokens": 723, "latency_ms": 7581.5, "usd": 0.122505, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"id\":\"ogs:core:dish:pico-de-gallo\",\"ogs_version\":\"0.1.0\",\"name\":\"Pico de Gallo\",\"cuisine\":\"Mexican\",\"course\":\"appetizer\",\"service_temperature\":\"cool\",\"components\":[{\"role\":\"main_vegetable\",\"ingredient_ref\":\"ogs:core:ingredient:tomato\",\"cooking_method\":\"raw\",\"proportion\":\"dominant\"},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:onion\",\"cooking_method\":\"raw\",\"proportion\":\"significant\"},{\"role\":\"aromatic_garnish\",\"ingredient_ref\":\"ogs:core:ingredient:cilantro\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"seasoning\",\"ingredient_ref\":\"ogs:core:ingredient:jalapeno\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"acid_component\",\"ingredient_ref\":\"ogs:core:ingredient:lime\",\"cooking_method\":\"raw\",\"proportion\":\"accent\"},{\"role\":\"seasoning\",\"ingredient_ref\":\"ogs:core:ingredient:salt\",\"proportion\":\"trace\"}],\"overall_sensory_profile\":{\"basic_tastes\":{\"sweet\":2,\"sour\":6,\"salty\":4,\"bitter\":1,\"umami\":3},\"structural\":{\"body\":3,\"acidity_perception\":7},\"aromatics\":[{\"family\":\"vegetal\",\"group\":\"fresh_vegetable\",\"item\":\"tomato\",\"qualifier\":\"fresh\",\"intensity\":6},{\"family\":\"herbal\",\"group\":\"fresh_herb\",\"item\":\"cilantro\",\"qualifier\":\"fresh\",\"intensity\":6},{\"family\":\"vegetal\",\"group\":\"allium\",\"item\":\"onion\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"spice\",\"group\":\"chili\",\"item\":\"jalapeno\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"fruit\",\"group\":\"citrus\",\"item\":\"lime\",\"qualifier\":\"fresh\",\"intensity\":5}],\"texture\":[\"juicy\",\"crunchy\",\"chunky\"],\"finish_length\":4,\"complexity\":5}}", "compliant": true, "score": 1.0, "detail": { "schema_valid": true, "schema_errors": [], "consistent": true, "required_fields": { "id": { "predicted": "ogs:core:dish:pico-de-gallo", "expected": "ogs:core:dish:pico-de-gallo", "match": true }, "ogs_version": { "predicted": "0.1.0", "expected": "0.1.0", "match": true } } }, "metrics": { "input_tokens": 4552, "output_tokens": 723, "latency_ms": 7751.7, "usd": 0.122505, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 4552.0, "output_tokens_mean": 724.667, "latency_ms_mean": 8111.9, "usd_sum": 0.36789 } }, { "task_id": "ogs:core:benchmark-task:struct-018", "category": "structured_output", "capability": "sensory_profile_json", "difficulty": "medium", "cuisine_region": "french", "scorer": "json_match", "context_needs": [ "scales.basic_tastes", "scales.structural", "vocab.aromatic_families", "vocab.qualifiers" ], "prompt_template_hash": "1470a28b8e9ef028", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nProduce a JSON sensory profile for 24-month aged Comté cheese. Keys: basic_tastes, structural, aromatics. All intensities on 0-10. JSON only.\n\nINPUT:\n{\n \"item\": \"24-month aged Comté\"\n}\n\nANSWER FORMAT: json", "expected": { "value": { "basic_tastes": { "sweet": 2.0, "sour": 2.0, "salty": 5.0, "bitter": 1.5, "umami": 8.0 }, "structural": { "body": 7.0, "acidity_perception": 3.0, "tannin": 0, "astringency": 0, "alcohol_heat": 0, "effervescence": 0 } }, "required_keys": [ "basic_tastes.umami", "basic_tastes.salty", "structural.body" ] }, "samples": [ { "sample": 0, "raw_response": "{\"basic_tastes\":{\"sweet\":4,\"sour\":2,\"salty\":6,\"bitter\":1.5,\"umami\":8.5},\"structural\":{\"body\":7.5,\"acidity_perception\":3,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"dairy\",\"qualifier\":\"cooked\",\"intensity\":8},{\"family\":\"savory\",\"qualifier\":\"cooked\",\"intensity\":7.5},{\"family\":\"fruit\",\"qualifier\":\"dried\",\"intensity\":6},{\"family\":\"earth\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"spice\",\"qualifier\":\"dried\",\"intensity\":3.5},{\"family\":\"confection\",\"qualifier\":\"cooked\",\"intensity\":4}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 8.5, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 6, "expected": 5.0, "match": true }, "structural.body": { "predicted": 7.5, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 725, "output_tokens": 262, "latency_ms": 3865.6, "usd": 0.030525, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"basic_tastes\":{\"sweet\":4,\"sour\":2,\"salty\":6,\"bitter\":1.5,\"umami\":8.5},\"structural\":{\"body\":7.5,\"acidity_perception\":3,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"dairy\",\"qualifier\":\"cooked\",\"intensity\":8},{\"family\":\"fruit\",\"qualifier\":\"dried\",\"intensity\":6.5},{\"family\":\"savory\",\"qualifier\":\"cooked\",\"intensity\":7},{\"family\":\"earth\",\"qualifier\":\"fresh\",\"intensity\":4},{\"family\":\"spice\",\"qualifier\":\"dried\",\"intensity\":3.5},{\"family\":\"confection\",\"qualifier\":\"cooked\",\"intensity\":5}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 8.5, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 6, "expected": 5.0, "match": true }, "structural.body": { "predicted": 7.5, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 725, "output_tokens": 262, "latency_ms": 3567.3, "usd": 0.030525, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\"basic_tastes\":{\"sweet\":4,\"sour\":2,\"salty\":5.5,\"bitter\":1.5,\"umami\":8.5},\"structural\":{\"body\":7.5,\"acidity_perception\":3,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":0,\"effervescence\":0},\"aromatics\":[{\"family\":\"dairy\",\"qualifier\":\"cooked\",\"intensity\":7.5},{\"family\":\"fruit\",\"qualifier\":\"dried\",\"intensity\":6},{\"family\":\"savory\",\"qualifier\":\"cooked\",\"intensity\":7},{\"family\":\"earth\",\"qualifier\":\"fresh\",\"intensity\":4},{\"family\":\"spice\",\"qualifier\":\"dried\",\"intensity\":3},{\"family\":\"confection\",\"qualifier\":\"cooked\",\"intensity\":5}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.umami": { "predicted": 8.5, "expected": 8.0, "match": true }, "basic_tastes.salty": { "predicted": 5.5, "expected": 5.0, "match": true }, "structural.body": { "predicted": 7.5, "expected": 7.0, "match": true } } }, "metrics": { "input_tokens": 725, "output_tokens": 262, "latency_ms": 4499.3, "usd": 0.030525, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 725.0, "output_tokens_mean": 262.0, "latency_ms_mean": 3977.4, "usd_sum": 0.091575 } }, { "task_id": "ogs:core:benchmark-task:struct-019", "category": "structured_output", "capability": "sensory_profile_json", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "json_match", "context_needs": [ "scales.basic_tastes", "scales.structural", "vocab.aromatic_families", "vocab.qualifiers" ], "prompt_template_hash": "aa2726470aa7cfb8", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Basic tastes scale (0-10)\n\nEach of `sweet`, `sour`, `salty`, `bitter`, `umami` is rated on a\n0-10 intensity scale where 0 = not detectable, 5 = clearly present,\n10 = overwhelming. Use decimals when precision helps (e.g. 8.5).\n\n### Structural attributes scale (0-10)\n\n`body`, `acidity_perception`, `tannin`, `astringency`, `alcohol_heat`,\n`effervescence` are each rated on the same 0-10 scale as basic tastes.\n\n### Aromatic families\n\nfruit, floral, herbal, spice, earth, wood, dairy, savory, confection, vegetal, marine\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nProduce a JSON sensory profile for blistered shishito peppers lightly salted. Keys: basic_tastes, structural, aromatics.\n\nINPUT:\n{\n \"item\": \"blistered shishito peppers with flaky salt\"\n}\n\nANSWER FORMAT: json", "expected": { "value": { "basic_tastes": { "sweet": 2.0, "sour": 1.0, "salty": 5.0, "bitter": 3.0, "umami": 2.0 }, "structural": { "body": 3.0, "acidity_perception": 2.0, "tannin": 0, "astringency": 1.0, "alcohol_heat": 0, "effervescence": 0 } }, "required_keys": [ "basic_tastes.salty", "basic_tastes.bitter", "structural.body" ] }, "samples": [ { "sample": 0, "raw_response": "{\"basic_tastes\":{\"sweet\":2,\"sour\":1,\"salty\":6,\"bitter\":3,\"umami\":4},\"structural\":{\"body\":3,\"acidity_perception\":1,\"tannin\":0,\"astringency\":1,\"alcohol_heat\":2,\"effervescence\":0},\"aromatics\":[{\"family\":\"vegetal\",\"qualifier\":\"cooked\",\"intensity\":7},{\"family\":\"vegetal\",\"qualifier\":\"fresh\",\"intensity\":5},{\"family\":\"savory\",\"qualifier\":\"cooked\",\"intensity\":5},{\"family\":\"earth\",\"qualifier\":\"cooked\",\"intensity\":3},{\"family\":\"spice\",\"qualifier\":\"fresh\",\"intensity\":2}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 6, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 3, "expected": 3.0, "match": true }, "structural.body": { "predicted": 3, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 719, "output_tokens": 232, "latency_ms": 2971.3, "usd": 0.028185, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "{\"basic_tastes\":{\"sweet\":2,\"sour\":1,\"salty\":5,\"bitter\":3,\"umami\":4},\"structural\":{\"body\":3,\"acidity_perception\":1.5,\"tannin\":1,\"astringency\":2,\"alcohol_heat\":2,\"effervescence\":0},\"aromatics\":[{\"family\":\"vegetal\",\"qualifier\":\"cooked\",\"intensity\":7},{\"family\":\"earth\",\"qualifier\":\"cooked\",\"intensity\":4},{\"family\":\"spice\",\"qualifier\":\"fresh\",\"intensity\":3},{\"family\":\"savory\",\"qualifier\":\"cooked\",\"intensity\":4}]}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 5, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 3, "expected": 3.0, "match": true }, "structural.body": { "predicted": 3, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 719, "output_tokens": 208, "latency_ms": 3152.1, "usd": 0.026385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\n \"basic_tastes\": {\n \"sweet\": 2,\n \"sour\": 1,\n \"salty\": 5,\n \"bitter\": 3.5,\n \"umami\": 3\n },\n \"structural\": {\n \"body\": 3,\n \"acidity_perception\": 2,\n \"tannin\": 0,\n \"astringency\": 1.5,\n \"alcohol_heat\": 0,\n \"effervescence\": 0\n },\n \"aromatics\": [\n {\"family\": \"vegetal\", \"qualifier\": \"cooked\", \"intensity\": 7},\n {\"family\": \"vegetal\", \"qualifier\": \"fresh\", \"intensity\": 4},\n {\"family\": \"earth\", \"qualifier\": \"cooked\", \"intensity\": 4.5},\n {\"family\": \"savory\", \"qualifier\": \"cooked\", \"intensity\": 3.5},\n {\"family\": \"spice\", \"qualifier\": \"fresh\", \"intensity\": 2}\n ]\n}", "compliant": true, "score": 1.0, "detail": { "per_key": { "basic_tastes.salty": { "predicted": 5, "expected": 5.0, "match": true }, "basic_tastes.bitter": { "predicted": 3.5, "expected": 3.0, "match": true }, "structural.body": { "predicted": 3, "expected": 3.0, "match": true } } }, "metrics": { "input_tokens": 719, "output_tokens": 312, "latency_ms": 4097.3, "usd": 0.034185, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 719.0, "output_tokens_mean": 250.667, "latency_ms_mean": 3406.9, "usd_sum": 0.088755 } }, { "task_id": "ogs:core:benchmark-task:struct-020", "category": "structured_output", "capability": "schema_valid_pairing", "difficulty": "expert", "cuisine_region": "mexican", "scorer": "schema_validation", "context_needs": [ "schema.pairing", "vocab.match_types", "vocab.explanation_codes", "vocab.grade_scale", "id.format", "ogs_version" ], "prompt_template_hash": "5b115600e8dad71f", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS pairing schema (`schema/pairing.schema.json`)\n\n```json\n{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://opengastronomy.org/schema/v0.2/pairing.schema.json\",\n \"title\": \"OGS Pairing\",\n \"description\": \"A scored, explained pairing between a dish and a beverage.\",\n \"type\": \"object\",\n \"required\": [\n \"id\",\n \"ogs_version\",\n \"name\",\n \"dish_ref\",\n \"beverage_ref\",\n \"match_types\",\n \"overall_score\",\n \"grade\",\n \"explanation_codes\",\n \"confidence\"\n ],\n \"properties\": {\n \"id\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:pairing:[a-z0-9-]+$\"\n },\n \"ogs_version\": {\n \"type\": \"string\",\n \"pattern\": \"^0\\\\.(1|2)\\\\.\\\\d+$\"\n },\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"available_languages\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n }\n },\n \"name\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"dish_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:dish:[a-z0-9-]+$\"\n },\n \"beverage_ref\": {\n \"type\": \"string\",\n \"pattern\": \"^ogs:[a-z0-9-]+:beverage:[a-z0-9-]+$\"\n },\n \"match_types\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"$ref\": \"#/$defs/match_type_entry\"\n }\n },\n \"overall_score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"grade\": {\n \"type\": \"string\",\n \"enum\": [\n \"A+\",\n \"A\",\n \"B+\",\n \"B\",\n \"C+\",\n \"C\",\n \"D\",\n \"F\"\n ]\n },\n \"explanation_codes\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/explanation_code_entry\"\n }\n },\n \"risks\": {\n \"type\": \"array\",\n \"items\": {\n \"$ref\": \"#/$defs/risk_entry\"\n }\n },\n \"confidence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"evidence\": {\n \"$ref\": \"#/$defs/evidence\"\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"metadata\": {\n \"$ref\": \"#/$defs/metadata\"\n }\n },\n \"additionalProperties\": true,\n \"$defs\": {\n \"bcp47_tag\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\"\n },\n \"lstring\": {\n \"oneOf\": [\n {\n \"type\": \"string\",\n \"minLength\": 1\n },\n {\n \"type\": \"object\",\n \"minProperties\": 1,\n \"patternProperties\": {\n \"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$\": {\n \"type\": \"string\",\n \"minLength\": 1\n }\n },\n \"additionalProperties\": false\n },\n {\n \"type\": \"object\",\n \"required\": [\n \"labels\"\n ],\n \"properties\": {\n \"primary_language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"labels\": {\n \"type\": \"array\",\n \"minItems\": 1,\n \"items\": {\n \"type\": \"object\",\n \"required\": [\n \"value\",\n \"language\"\n ],\n \"properties\": {\n \"value\": {\n \"type\": \"string\",\n \"minLength\": 1\n },\n \"language\": {\n \"$ref\": \"#/$defs/bcp47_tag\"\n },\n \"script\": {\n \"type\": \"string\",\n \"pattern\": \"^[A-Z][a-z]{3}$\"\n },\n \"role\": {\n \"type\": \"string\",\n \"enum\": [\n \"preferred\",\n \"alternate\",\n \"transliteration\",\n \"descriptive\",\n \"loan\",\n \"historical\",\n \"deprecated\",\n \"ipa\"\n ]\n },\n \"transliteration_scheme\": {\n \"type\": \"string\"\n },\n \"translation\": {\n \"type\": \"object\",\n \"additionalProperties\": true\n }\n },\n \"additionalProperties\": false\n }\n }\n },\n \"additionalProperties\": false\n }\n ]\n },\n \"match_type_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"type\",\n \"score\"\n ],\n \"properties\": {\n \"type\": {\n \"type\": \"string\",\n \"enum\": [\n \"harmony\",\n \"contrast\",\n \"bridge\",\n \"intensity_alignment\",\n \"structural_balance\",\n \"refresh\"\n ]\n },\n \"score\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"primary\": {\n \"type\": \"boolean\"\n }\n },\n \"additionalProperties\": false\n },\n \"explanation_code_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"weight\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"detail\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"risk_entry\": {\n \"type\": \"object\",\n \"required\": [\n \"code\",\n \"severity\"\n ],\n \"properties\": {\n \"code\": {\n \"type\": \"string\"\n },\n \"severity\": {\n \"type\": \"string\",\n \"enum\": [\n \"low\",\n \"medium\",\n \"high\"\n ]\n },\n \"description\": {\n \"$ref\": \"#/$defs/lstring\"\n },\n \"mitigation\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": false\n },\n \"evidence\": {\n \"type\": \"object\",\n \"properties\": {\n \"method\": {\n \"type\": \"string\",\n \"enum\": [\n \"expert_panel\",\n \"instrumental\",\n \"computed\",\n \"estimated\"\n ]\n },\n \"sources\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"notes\": {\n \"$ref\": \"#/$defs/lstring\"\n }\n },\n \"additionalProperties\": true\n },\n \"metadata\": {\n \"type\": \"object\",\n \"properties\": {\n \"created\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"updated\": {\n \"type\": \"string\",\n \"format\": \"date-time\"\n },\n \"source\": {\n \"type\": \"string\"\n },\n \"license\": {\n \"type\": \"string\"\n }\n },\n \"additionalProperties\": true\n }\n }\n}\n```\n\n### Match types\n\nharmony, contrast, bridge, intensity_alignment, structural_balance, refresh\n\n### OGS Explanation Codes\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**negative**\n- `RISK_TANNIN_FISH` — Tannin-Fish Clash: Tannins interact with fish oils to produce metallic, unpleasant off-flavors.\n- `RISK_ALCOHOL_OVERPOWERS` — Alcohol Overpowers Dish: High alcohol content overwhelms the dish's delicate flavors with heat and bitterness.\n- `RISK_BITTER_AMPLIFY` — Bitterness Amplification: Bitterness in both dish and beverage compounds to an unpleasant level.\n- `RISK_OAK_MASKS` — Oak Masks Dish: Heavy oak influence in the beverage masks or overwhelms the dish's subtle flavors.\n- `RISK_INTENSITY_MISMATCH` — Intensity Mismatch: One element is significantly more intense than the other, causing the weaker to be lost.\n- `RISK_ACID_CLASH` — Acid Clash: Excessive acidity from both dish and beverage creates an unpleasantly sharp experience.\n- `RISK_SWEETNESS_CONFLICT` — Sweetness Conflict: The dish makes the beverage taste less sweet, thin, or overly acidic.\n- `RISK_SPICE_ALCOHOL` — Spice-Alcohol Amplification: High alcohol amplifies the heat of spicy dishes to an uncomfortable level.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n### Grade scale (derived from 0-100 overall_score)\n\n- **A+**: 95-100\n- **A**: 90-94\n- **B+**: 85-89\n- **B**: 80-84\n- **C+**: 75-79\n- **C**: 70-74\n- **D**: 60-69\n- **F**: <60\n\n### OGS ID format\n\nAll OGS entity IDs follow the pattern:\n\n ogs:::\n\n- `namespace` is lowercase alphanumeric with hyphens, e.g. `core`.\n- `entity-type` is one of `ingredient`, `dish`, `beverage`, `pairing`,\n `benchmark-task`, etc.\n- `slug` is lowercase alphanumeric with hyphens.\n\nExample: `ogs:core:ingredient:fleur-de-sel`.\n\n### OGS version\n\nAll produced documents must set `ogs_version` to **\"0.1.0\"**.\n\n---\n\nProduce an OGS pairing JSON for mole-negro enchiladas with Aragonese Garnacha. JSON only.\n\nINPUT:\n{\n \"pairing_slug\": \"mole-negro-garnacha\",\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"intent\": \"Cross-cultural bridge pairing: ripe fruit and body handle chocolate-chile sauce.\"\n}\n\nANSWER FORMAT: json", "expected": { "schema_ref": "schema/pairing.schema.json", "required_fields": { "id": "ogs:core:pairing:mole-negro-garnacha", "ogs_version": "0.1.0", "dish_ref": "ogs:core:dish:mole-negro-enchiladas", "beverage_ref": "ogs:core:beverage:garnacha-aragon" } }, "samples": [ { "sample": 0, "raw_response": "{\n \"id\": \"ogs:core:pairing:mole-negro-garnacha\",\n \"ogs_version\": \"0.1.0\",\n \"name\": \"Mole Negro Enchiladas with Aragonese Garnacha\",\n \"description\": \"A cross-cultural pairing where ripe-fruited, full-bodied Garnacha meets the deep chocolate, chile, and spice complexity of mole negro.\",\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"bridge\",\n \"score\": 88,\n \"description\": \"Ripe dark fruit and subtle spice in Garnacha bridge the chocolate, dried chile, and spice layers of mole negro.\",\n \"primary\": true\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 86,\n \"description\": \"Full-bodied, concentrated Garnacha matches the intensity of the complex mole sauce.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 82,\n \"description\": \"Warm, earthy, and spicy aromatics converge between dish and wine.\"\n },\n {\n \"type\": \"structural_balance\",\n \"score\": 80,\n \"description\": \"Moderate tannin and generous body support the richness of the sauce without overwhelming the tortilla and filling.\"\n }\n ],\n \"overall_score\": 88,\n \"grade\": \"B+\",\n \"explanation_codes\": [\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.9,\n \"detail\": \"Dried chile, clove, and cinnamon notes in mole echo the spicy aromatics of Aragonese Garnacha.\"\n },\n {\n \"code\": \"AROMA_SHARED_FRUIT\",\n \"weight\": 0.8,\n \"detail\": \"Ripe black and red fruit in the wine bridges the raisin and dried fruit notes in mole negro.\"\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.85,\n \"detail\": \"The full body of Garnacha aligns with the dense, velvety mole sauce.\"\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.85,\n \"detail\": \"Both elements are highly intense and complex, keeping neither side dominant.\"\n },\n {\n \"code\": \"STRUCT_ALCOHOL_WARMTH\",\n \"weight\": 0.6,\n \"detail\": \"Garnacha's warmth complements the hearty, slow-cooked character of the dish.\"\n },\n {\n \"code\": \"HARMONY_COMPLEXITY_MATCH\",\n \"weight\": 0.75,\n \"detail\": \"Mole negro's layered complexity is met by the nuanced profile of a quality Aragonese Garnacha.\"\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_SPICE_ALCOHOL\",", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "[{'type': 'bridge', 'score': 88, 'description': 'Ripe dark fruit and subtle spice in Garnacha bridge the chocolate, dried chile, and spice layers of mole negro.', 'primary': True}, {'type': 'intensity_alignment', 'score': 86, 'description': 'Full-bodied, concentrated Garnacha matches the intensity of the complex mole sauce.'}, {'type': 'harmony', 'score': 82, 'description': 'Warm, earthy, and spicy aromatics converge between dish and wine.'}, {'type': 'structural_balance', 'score': 80, 'description': 'Moderate tannin and generous body support the richness of the sauce without overwhelming the tortilla and filling.'}] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:pairing:mole-negro-garnacha", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "dish_ref": { "predicted": null, "expected": "ogs:core:dish:mole-negro-enchiladas", "match": false }, "beverage_ref": { "predicted": null, "expected": "ogs:core:beverage:garnacha-aragon", "match": false } } }, "metrics": { "input_tokens": 5472, "output_tokens": 1024, "latency_ms": 13258.7, "usd": 0.15888, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } }, { "sample": 1, "raw_response": "{\"id\":\"ogs:core:pairing:mole-negro-garnacha\",\"ogs_version\":\"0.1.0\",\"name\":\"Mole Negro Enchiladas with Aragonese Garnacha\",\"dish_ref\":\"ogs:core:dish:mole-negro-enchiladas\",\"beverage_ref\":\"ogs:core:beverage:garnacha-aragon\",\"match_types\":[{\"type\":\"bridge\",\"score\":88,\"primary\":true},{\"type\":\"intensity_alignment\",\"score\":85},{\"type\":\"harmony\",\"score\":82}],\"overall_score\":87,\"grade\":\"B+\",\"explanation_codes\":[{\"code\":\"AROMA_SHARED_SPICE\",\"weight\":0.3,\"detail\":\"Dark chile and spice notes in mole negro echo the peppery, spiced character of Aragonese Garnacha.\"},{\"code\":\"AROMA_SHARED_FRUIT\",\"weight\":0.2,\"detail\":\"Dried fruit notes (raisin, prune) in mole bridge with Garnacha's ripe red and black fruit.\"},{\"code\":\"STRUCT_INTENSITY_MATCH\",\"weight\":0.25,\"detail\":\"The full body and ripe intensity of Garnacha stand up to the deep, concentrated mole sauce.\"},{\"code\":\"STRUCT_SWEET_OFFSET\",\"weight\":0.15,\"detail\":\"Garnacha's ripe fruit sweetness offsets the bitter chocolate and chile heat in the mole.\"},{\"code\":\"STRUCT_TANNIN_PROTEIN\",\"weight\":0.1,\"detail\":\"Moderate tannins integrate with the protein in the enchiladas, softening astringency.\"}],\"risks\":[{\"code\":\"RISK_SPICE_ALCOHOL\",\"severity\":\"medium\",\"description\":\"High alcohol in some Aragonese Garnachas can amplify chile heat.\",\"mitigation\":\"Serve slightly cool (15-16°C) and choose a Garnacha under 14.5% ABV.\"},{\"code\":\"RISK_BITTER_AMPLIFY\",\"severity\":\"low\",\"description\":\"Bitter cacao in mole combined with wine tannins could compound bitterness.\",\"mitigation\":\"Select a Garnacha with softer tannins and ripe, generous fruit.\"}],\"confidence\":0.8,\"evidence\":{\"method\":\"expert_panel\",\"notes\":\"Cross-cultural bridge pairing leveraging shared spice and ripe-fruit aromatics to tame mole negro's complexity.\"}}", "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": 5472, "output_tokens": 828, "latency_ms": 11817.1, "usd": 0.14418, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "{\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, dark-fruited Garnacha from Aragón meets the complex chocolate-chile depth of mole negro.\",\n \"dish_ref\": \"ogs:core:dish:mole-negro-enchiladas\",\n \"beverage_ref\": \"ogs:core:beverage:garnacha-aragon\",\n \"match_types\": [\n {\n \"type\": \"bridge\",\n \"score\": 88,\n \"description\": \"Ripe dark fruit and subtle spice in Garnacha bridge the chocolate, dried chile, and spice layers of mole negro.\",\n \"primary\": true\n },\n {\n \"type\": \"intensity_alignment\",\n \"score\": 86,\n \"description\": \"Full-bodied, concentrated Garnacha matches the deep, layered intensity of mole negro.\"\n },\n {\n \"type\": \"harmony\",\n \"score\": 82,\n \"description\": \"Warm, rustic character of both elements converges into a unified, hearty experience.\"\n }\n ],\n \"overall_score\": 87,\n \"grade\": \"B+\",\n \"explanation_codes\": [\n {\n \"code\": \"AROMA_SHARED_FRUIT\",\n \"weight\": 0.7,\n \"detail\": \"Dark dried-fruit notes in Garnacha echo the raisin and prune tones of mole negro.\"\n },\n {\n \"code\": \"AROMA_SHARED_SPICE\",\n \"weight\": 0.8,\n \"detail\": \"Warm spice aromatics in both the wine and the mole (clove, cinnamon, pepper) bridge the pairing.\"\n },\n {\n \"code\": \"STRUCT_INTENSITY_MATCH\",\n \"weight\": 0.85,\n \"detail\": \"Both elements are bold and concentrated, so neither overwhelms the other.\"\n },\n {\n \"code\": \"STRUCT_BODY_ALIGN\",\n \"weight\": 0.8,\n \"detail\": \"Full-bodied Garnacha aligns with the rich, viscous body of mole sauce.\"\n },\n {\n \"code\": \"STRUCT_ALCOHOL_WARMTH\",\n \"weight\": 0.6,\n \"detail\": \"Garnacha's warmth complements the hearty, earthy mole without overpowering.\"\n },\n {\n \"code\": \"HARMONY_COMPLEXITY_MATCH\",\n \"weight\": 0.75,\n \"detail\": \"The layered complexity of mole negro is matched by Garnacha's multifaceted aromatic profile.\"\n }\n ],\n \"risks\": [\n {\n \"code\": \"RISK_SPICE_ALCOHOL\",\n \"severity\": \"medium\",\n \"description\": \"Higher-alcohol Garnacha can amplify the chile heat in mole negro.\",\n \"mitigation\": \"Choose a balanced Garnacha around 14%", "compliant": true, "score": 0.0, "detail": { "schema_valid": false, "schema_errors": [ "[{'type': 'bridge', 'score': 88, 'description': 'Ripe dark fruit and subtle spice in Garnacha bridge the chocolate, dried chile, and spice layers of mole negro.', 'primary': True}, {'type': 'intensity_alignment', 'score': 86, 'description': 'Full-bodied, concentrated Garnacha matches the deep, layered intensity of mole negro.'}, {'type': 'harmony', 'score': 82, 'description': 'Warm, rustic character of both elements converges into a unified, hearty experience.'}] is not of type 'object'" ], "consistent": false, "required_fields": { "id": { "predicted": null, "expected": "ogs:core:pairing:mole-negro-garnacha", "match": false }, "ogs_version": { "predicted": null, "expected": "0.1.0", "match": false }, "dish_ref": { "predicted": null, "expected": "ogs:core:dish:mole-negro-enchiladas", "match": false }, "beverage_ref": { "predicted": null, "expected": "ogs:core:beverage:garnacha-aragon", "match": false } } }, "metrics": { "input_tokens": 5472, "output_tokens": 1024, "latency_ms": 12944.2, "usd": 0.15888, "model_version": "claude-opus-4-7", "finish_reason": "max_tokens" } } ], "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": 5472.0, "output_tokens_mean": 958.667, "latency_ms_mean": 12673.333, "usd_sum": 0.46194 } }, { "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": 530, "output_tokens": 7, "latency_ms": 1128.7, "usd": 0.008475, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 530, "output_tokens": 7, "latency_ms": 920.8, "usd": 0.008475, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "fruit", "compliant": true, "score": 1.0, "detail": { "predicted": "fruit", "expected": "fruit", "aliases": [] }, "metrics": { "input_tokens": 530, "output_tokens": 7, "latency_ms": 1265.8, "usd": 0.008475, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 530.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1105.1, "usd_sum": 0.025425 } }, { "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": 513, "output_tokens": 6, "latency_ms": 1801.1, "usd": 0.008145, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 513, "output_tokens": 6, "latency_ms": 794.2, "usd": 0.008145, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "earth", "compliant": true, "score": 1.0, "detail": { "predicted": "earth", "expected": "earth", "aliases": [] }, "metrics": { "input_tokens": 513, "output_tokens": 6, "latency_ms": 1101.2, "usd": 0.008145, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 513.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1232.167, "usd_sum": 0.024435 } }, { "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": 516, "output_tokens": 6, "latency_ms": 1490.2, "usd": 0.00819, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 516, "output_tokens": 6, "latency_ms": 1307.2, "usd": 0.00819, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "savory", "compliant": true, "score": 1.0, "detail": { "predicted": "savory", "expected": "savory", "aliases": [] }, "metrics": { "input_tokens": 516, "output_tokens": 6, "latency_ms": 1456.7, "usd": 0.00819, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 6.0, "latency_ms_mean": 1418.033, "usd_sum": 0.02457 } }, { "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": 636, "output_tokens": 6, "latency_ms": 1159.3, "usd": 0.00999, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 636, "output_tokens": 6, "latency_ms": 949.5, "usd": 0.00999, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "confit", "compliant": true, "score": 1.0, "detail": { "predicted": "confit", "expected": "confit", "aliases": [] }, "metrics": { "input_tokens": 636, "output_tokens": 6, "latency_ms": 1186.1, "usd": 0.00999, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 636.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1098.3, "usd_sum": 0.02997 } }, { "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": 524, "output_tokens": 7, "latency_ms": 992.8, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "bridge", "compliant": true, "score": 1.0, "detail": { "predicted": "bridge", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 524, "output_tokens": 7, "latency_ms": 2033.1, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "bridge", "compliant": true, "score": 1.0, "detail": { "predicted": "bridge", "expected": "bridge", "aliases": [] }, "metrics": { "input_tokens": 524, "output_tokens": 7, "latency_ms": 1554.3, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 524.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1526.733, "usd_sum": 0.025155 } }, { "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": 559, "output_tokens": 7, "latency_ms": 908.9, "usd": 0.00891, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 559, "output_tokens": 7, "latency_ms": 901.4, "usd": 0.00891, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "sauce", "compliant": true, "score": 1.0, "detail": { "predicted": "sauce", "expected": "sauce", "aliases": [] }, "metrics": { "input_tokens": 559, "output_tokens": 7, "latency_ms": 1140.0, "usd": 0.00891, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 559.0, "output_tokens_mean": 7.0, "latency_ms_mean": 983.433, "usd_sum": 0.02673 } }, { "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": 481, "output_tokens": 6, "latency_ms": 1218.6, "usd": 0.007665, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 481, "output_tokens": 6, "latency_ms": 1630.2, "usd": 0.007665, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "candied", "compliant": true, "score": 1.0, "detail": { "predicted": "candied", "expected": "candied", "aliases": [] }, "metrics": { "input_tokens": 481, "output_tokens": 6, "latency_ms": 1068.6, "usd": 0.007665, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 481.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1305.8, "usd_sum": 0.022995 } }, { "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": 569, "output_tokens": 5, "latency_ms": 1074.1, "usd": 0.00891, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 569, "output_tokens": 5, "latency_ms": 905.2, "usd": 0.00891, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "A", "compliant": true, "score": 1.0, "detail": { "predicted": "A", "expected": "A", "aliases": [] }, "metrics": { "input_tokens": 569, "output_tokens": 5, "latency_ms": 2317.2, "usd": 0.00891, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 569.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1432.167, "usd_sum": 0.02673 } }, { "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": 529, "output_tokens": 6, "latency_ms": 1558.8, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 529, "output_tokens": 6, "latency_ms": 1343.9, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "spice", "compliant": true, "score": 1.0, "detail": { "predicted": "spice", "expected": "spice", "aliases": [] }, "metrics": { "input_tokens": 529, "output_tokens": 6, "latency_ms": 2100.4, "usd": 0.008385, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 529.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1667.7, "usd_sum": 0.025155 } }, { "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": 525, "output_tokens": 6, "latency_ms": 1005.9, "usd": 0.008325, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 525, "output_tokens": 6, "latency_ms": 932.7, "usd": 0.008325, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "marine", "compliant": true, "score": 1.0, "detail": { "predicted": "marine", "expected": "marine", "aliases": [] }, "metrics": { "input_tokens": 525, "output_tokens": 6, "latency_ms": 2182.9, "usd": 0.008325, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 525.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1373.833, "usd_sum": 0.024975 } }, { "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": 617, "output_tokens": 7, "latency_ms": 1028.0, "usd": 0.00978, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 617, "output_tokens": 7, "latency_ms": 1883.2, "usd": 0.00978, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "roasted", "compliant": true, "score": 1.0, "detail": { "predicted": "roasted", "expected": "roasted", "aliases": [] }, "metrics": { "input_tokens": 617, "output_tokens": 7, "latency_ms": 1031.9, "usd": 0.00978, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 617.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1314.367, "usd_sum": 0.02934 } }, { "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": 625, "output_tokens": 6, "latency_ms": 1092.0, "usd": 0.009825, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 625, "output_tokens": 6, "latency_ms": 1124.2, "usd": 0.009825, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "cured", "compliant": true, "score": 1.0, "detail": { "predicted": "cured", "expected": "cured", "aliases": [] }, "metrics": { "input_tokens": 625, "output_tokens": 6, "latency_ms": 913.1, "usd": 0.009825, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 625.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1043.1, "usd_sum": 0.029475 } }, { "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": 551, "output_tokens": 8, "latency_ms": 1158.7, "usd": 0.008865, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 551, "output_tokens": 8, "latency_ms": 996.9, "usd": 0.008865, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "seasoning", "compliant": true, "score": 1.0, "detail": { "predicted": "seasoning", "expected": "seasoning", "aliases": [] }, "metrics": { "input_tokens": 551, "output_tokens": 8, "latency_ms": 1143.0, "usd": 0.008865, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 551.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1099.533, "usd_sum": 0.026595 } }, { "task_id": "ogs:core:benchmark-task:vocab-014", "category": "vocabulary", "capability": "qualifier_vocabulary", "difficulty": "medium", "cuisine_region": "chinese", "scorer": "exact_match", "context_needs": [ "vocab.qualifiers" ], "prompt_template_hash": "3980456a47e9b7c6", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### Aromatic qualifiers\n\nfresh, dried, cooked, candied, fermented, zest, overripe\n\n---\n\nSelect the OGS aromatic qualifier that best describes the state of Sichuan peppercorn as it is commonly used — whole, toasted, and ground over finished mapo tofu.\n\nINPUT:\n{\n \"item\": \"Sichuan peppercorn (Zanthoxylum), whole, pan-toasted just before grinding over the dish\"\n}\n\nANSWER FORMAT: one_of:fresh,dried,cooked,candied,fermented,zest,overripe", "expected": { "value": "dried" }, "samples": [ { "sample": 0, "raw_response": "dried", "compliant": true, "score": 1.0, "detail": { "predicted": "dried", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 547, "output_tokens": 6, "latency_ms": 1575.8, "usd": 0.008655, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "dried", "compliant": true, "score": 1.0, "detail": { "predicted": "dried", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 547, "output_tokens": 6, "latency_ms": 1968.6, "usd": 0.008655, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "dried", "compliant": true, "score": 1.0, "detail": { "predicted": "dried", "expected": "dried", "aliases": [] }, "metrics": { "input_tokens": 547, "output_tokens": 6, "latency_ms": 1262.7, "usd": 0.008655, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 547.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1602.367, "usd_sum": 0.025965 } }, { "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": 549, "output_tokens": 6, "latency_ms": 1072.3, "usd": 0.008685, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 549, "output_tokens": 6, "latency_ms": 1805.4, "usd": 0.008685, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "C+", "compliant": true, "score": 1.0, "detail": { "predicted": "c+", "expected": "c+", "aliases": [] }, "metrics": { "input_tokens": 549, "output_tokens": 6, "latency_ms": 1279.2, "usd": 0.008685, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 549.0, "output_tokens_mean": 6.0, "latency_ms_mean": 1385.633, "usd_sum": 0.026055 } }, { "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": 517, "output_tokens": 7, "latency_ms": 889.5, "usd": 0.00828, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 517, "output_tokens": 7, "latency_ms": 895.9, "usd": 0.00828, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "refresh", "compliant": true, "score": 1.0, "detail": { "predicted": "refresh", "expected": "refresh", "aliases": [] }, "metrics": { "input_tokens": 517, "output_tokens": 7, "latency_ms": 2117.5, "usd": 0.00828, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "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": 7.0, "latency_ms_mean": 1300.967, "usd_sum": 0.02484 } }, { "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": 520, "output_tokens": 7, "latency_ms": 1358.7, "usd": 0.008325, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 520, "output_tokens": 7, "latency_ms": 1043.5, "usd": 0.008325, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "herbal", "compliant": true, "score": 1.0, "detail": { "predicted": "herbal", "expected": "herbal", "aliases": [] }, "metrics": { "input_tokens": 520, "output_tokens": 7, "latency_ms": 1213.4, "usd": 0.008325, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 520.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1205.2, "usd_sum": 0.024975 } }, { "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": 552, "output_tokens": 8, "latency_ms": 1048.8, "usd": 0.00888, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "acid_component", "compliant": true, "score": 1.0, "detail": { "predicted": "acid_component", "expected": "acid_component", "aliases": [] }, "metrics": { "input_tokens": 552, "output_tokens": 8, "latency_ms": 1831.5, "usd": 0.00888, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "acid_component", "compliant": true, "score": 1.0, "detail": { "predicted": "acid_component", "expected": "acid_component", "aliases": [] }, "metrics": { "input_tokens": 552, "output_tokens": 8, "latency_ms": 1284.9, "usd": 0.00888, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 552.0, "output_tokens_mean": 8.0, "latency_ms_mean": 1388.4, "usd_sum": 0.02664 } }, { "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": 625, "output_tokens": 7, "latency_ms": 1181.1, "usd": 0.0099, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 625, "output_tokens": 7, "latency_ms": 1205.1, "usd": 0.0099, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "fermented", "compliant": true, "score": 1.0, "detail": { "predicted": "fermented", "expected": "fermented", "aliases": [] }, "metrics": { "input_tokens": 625, "output_tokens": 7, "latency_ms": 2270.8, "usd": 0.0099, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 625.0, "output_tokens_mean": 7.0, "latency_ms_mean": 1552.333, "usd_sum": 0.0297 } }, { "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": 549, "output_tokens": 5, "latency_ms": 1158.8, "usd": 0.00861, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 549, "output_tokens": 5, "latency_ms": 975.2, "usd": 0.00861, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "D", "compliant": true, "score": 1.0, "detail": { "predicted": "d", "expected": "d", "aliases": [] }, "metrics": { "input_tokens": 549, "output_tokens": 5, "latency_ms": 1916.0, "usd": 0.00861, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 1.0, "score_summary": { "mean": 1.0, "stdev": 0.0, "sem": 0.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "n": 3 }, "score_if_valid": 1.0, "format_rate": 1.0, "metrics": { "input_tokens_mean": 549.0, "output_tokens_mean": 5.0, "latency_ms_mean": 1350.0, "usd_sum": 0.02583 } }, { "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": "[\"STRUCT_TANNIN_FAT\",\"STRUCT_UMAMI_ENHANCE\",\"STRUCT_BODY_ALIGN\",\"AROMA_SHARED_EARTH\",\"STRUCT_ACIDITY_BALANCE\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.7273, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "precision": 0.6667, "recall": 0.8 }, "metrics": { "input_tokens": 2127, "output_tokens": 110, "latency_ms": 2970.6, "usd": 0.040155, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_BODY_ALIGN\",\"STRUCT_TANNIN_FAT\",\"STRUCT_UMAMI_ENHANCE\",\"STRUCT_ACIDITY_BALANCE\",\"AROMA_SHARED_EARTH\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.7273, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "precision": 0.6667, "recall": 0.8 }, "metrics": { "input_tokens": 2127, "output_tokens": 110, "latency_ms": 3619.4, "usd": 0.040155, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"STRUCT_TANNIN_FAT\",\"STRUCT_BODY_ALIGN\",\"STRUCT_UMAMI_ENHANCE\",\"AROMA_SHARED_EARTH\",\"STRUCT_ACIDITY_BALANCE\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.5455, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "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": 2127, "output_tokens": 112, "latency_ms": 2143.7, "usd": 0.040305, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.105, "sem": 0.0606, "ci95_lo": 0.5479, "ci95_hi": 0.7855, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2127.0, "output_tokens_mean": 110.667, "latency_ms_mean": 2911.233, "usd_sum": 0.120615 } }, { "task_id": "ogs:core:benchmark-task:xplain-002", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "bdc5d8d74c85e9ab", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain the success of the pairing below. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"fresh oysters on the half shell with lemon\",\n \"beverage\": \"Chablis Premier Cru (Chardonnay, high acid, mineral, lean body)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_ACIDITY_BALANCE", "REFRESH_ACID", "REFRESH_MINERAL", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"REFRESH_ACID\",\"REFRESH_MINERAL\",\"AROMA_SHARED_EARTH\",\"STRUCT_ACIDITY_BALANCE\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 2074, "output_tokens": 76, "latency_ms": 1935.3, "usd": 0.03681, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"REFRESH_ACID\",\"REFRESH_MINERAL\",\"AROMA_SHARED_EARTH\",\"STRUCT_ACIDITY_BALANCE\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 2074, "output_tokens": 76, "latency_ms": 1732.8, "usd": 0.03681, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"REFRESH_ACID\",\"REFRESH_MINERAL\",\"AROMA_SHARED_EARTH\",\"STRUCT_ACIDITY_BALANCE\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 2074, "output_tokens": 76, "latency_ms": 5004.4, "usd": 0.03681, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8, "score_summary": { "mean": 0.8, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.8, "ci95_hi": 0.8, "n": 3 }, "score_if_valid": 0.8, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2074.0, "output_tokens_mean": 76.0, "latency_ms_mean": 2890.833, "usd_sum": 0.11043 } }, { "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": "[\"REFRESH_EFFERVESCE\",\"CONTRAST_RICH_CRISP\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\"]", "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": 2053, "output_tokens": 67, "latency_ms": 1838.2, "usd": 0.03582, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"REFRESH_EFFERVESCE\",\"CONTRAST_RICH_CRISP\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\"]", "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": 2053, "output_tokens": 67, "latency_ms": 1719.7, "usd": 0.03582, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\",\"CONTRAST_RICH_CRISP\"]", "compliant": true, "score": 1.0, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "expected": [ "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE" ], "precision": 1.0, "recall": 1.0 }, "metrics": { "input_tokens": 2053, "output_tokens": 48, "latency_ms": 1499.3, "usd": 0.034395, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.9047, "score_summary": { "mean": 0.9047, "stdev": 0.0825, "sem": 0.0476, "ci95_lo": 0.8114, "ci95_hi": 0.9981, "n": 3 }, "score_if_valid": 0.9047, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2053.0, "output_tokens_mean": 60.667, "latency_ms_mean": 1685.733, "usd_sum": 0.106035 } }, { "task_id": "ogs:core:benchmark-task:xplain-004", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "b3249dafda966f70", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain the success of the pairing below. Respond as a JSON array (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"seared foie gras on brioche (very rich, fatty, slightly sweet-savoury)\",\n \"beverage\": \"Sauternes (botrytised sweet white, high residual sugar, high acidity)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "STRUCT_ACIDITY_BALANCE", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\",\"CONTRAST_RICH_CRISP\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2081, "output_tokens": 86, "latency_ms": 2405.7, "usd": 0.037665, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"CONTRAST_SWEET_ACID\",\"CONTRAST_RICH_CRISP\",\"STRUCT_SWEET_OFFSET\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 2081, "output_tokens": 84, "latency_ms": 1650.7, "usd": 0.037515, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"CONTRAST_SWEET_ACID\",\"CONTRAST_RICH_CRISP\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2081, "output_tokens": 85, "latency_ms": 1802.6, "usd": 0.03759, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 2081.0, "output_tokens_mean": 85.0, "latency_ms_mean": 1953.0, "usd_sum": 0.11277 } }, { "task_id": "ogs:core:benchmark-task:xplain-005", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "0cb2f1946943a0e2", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS explanation codes that best explain why the pairing works. Respond as a JSON array (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"charcoal-grilled lamb rack with rosemary, black pepper crust, charred edges\",\n \"beverage\": \"Northern Rhone Syrah (Cote-Rotie) — black pepper, violet, smoked meat, moderate-high tannin\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "AROMA_SHARED_HERBAL", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_SPICE\",\"AROMA_SHARED_WOOD\",\"AROMA_SHARED_HERBAL\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "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": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 2096, "output_tokens": 90, "latency_ms": 1741.1, "usd": 0.03819, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_SPICE\",\"AROMA_SHARED_WOOD\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_FLAVOR_CONVERGE\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_SPICE", "AROMA_SHARED_WOOD", "HARMONY_FLAVOR_CONVERGE", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_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": 2096, "output_tokens": 94, "latency_ms": 2352.0, "usd": 0.03849, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_SPICE\",\"AROMA_SHARED_WOOD\",\"AROMA_SHARED_HERBAL\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "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": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 2096, "output_tokens": 90, "latency_ms": 2963.3, "usd": 0.03819, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.7333, "score_summary": { "mean": 0.7333, "stdev": 0.1155, "sem": 0.0667, "ci95_lo": 0.6027, "ci95_hi": 0.864, "n": 3 }, "score_if_valid": 0.7333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2096.0, "output_tokens_mean": 91.333, "latency_ms_mean": 2352.133, "usd_sum": 0.11487 } }, { "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": "[\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"AROMA_SHARED_HERBAL\",\"STRUCT_INTENSITY_MATCH\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2077, "output_tokens": 83, "latency_ms": 1827.6, "usd": 0.03738, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"HARMONY_REGIONAL\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\",\"AROMA_SHARED_HERBAL\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2077, "output_tokens": 83, "latency_ms": 2059.9, "usd": 0.03738, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\",\"AROMA_SHARED_HERBAL\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2077, "output_tokens": 83, "latency_ms": 4214.9, "usd": 0.03738, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8889, "score_summary": { "mean": 0.8889, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.8889, "ci95_hi": 0.8889, "n": 3 }, "score_if_valid": 0.8889, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2077.0, "output_tokens_mean": 83.0, "latency_ms_mean": 2700.8, "usd_sum": 0.11214 } }, { "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": "[\"STRUCT_SWEET_OFFSET\",\"CONTRAST_SWEET_SALTY\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\"]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.75, "recall": 0.75 }, "metrics": { "input_tokens": 2061, "output_tokens": 70, "latency_ms": 2042.4, "usd": 0.036165, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"CONTRAST_SWEET_ACID\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.75, "detail": { "predicted": [ "CONTRAST_SWEET_ACID", "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": 2061, "output_tokens": 68, "latency_ms": 1812.2, "usd": 0.036015, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"CONTRAST_SWEET_SALTY\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "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": 2061, "output_tokens": 69, "latency_ms": 2099.3, "usd": 0.03609, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8333, "score_summary": { "mean": 0.8333, "stdev": 0.1443, "sem": 0.0833, "ci95_lo": 0.67, "ci95_hi": 0.9967, "n": 3 }, "score_if_valid": 0.8333, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2061.0, "output_tokens_mean": 69.0, "latency_ms_mean": 1984.633, "usd_sum": 0.10827 } }, { "task_id": "ogs:core:benchmark-task:xplain-008", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "medium", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "2120f96a0444a50e", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"herb-crusted rack of lamb, medium-rare\",\n \"beverage\": \"Northern Rhône Syrah\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_TANNIN_PROTEIN", "AROMA_SHARED_HERBAL", "STRUCT_BODY_ALIGN", "HARMONY_FLAVOR_CONVERGE" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2059, "output_tokens": 89, "latency_ms": 1607.1, "usd": 0.03756, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2059, "output_tokens": 89, "latency_ms": 1903.8, "usd": 0.03756, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_HERBAL\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_BODY_ALIGN\",\"HARMONY_FLAVOR_CONVERGE\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_FLAVOR_CONVERGE", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "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": 2059, "output_tokens": 96, "latency_ms": 1916.9, "usd": 0.038085, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.7408, "score_summary": { "mean": 0.7408, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.5956, "ci95_hi": 0.8859, "n": 3 }, "score_if_valid": 0.7408, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2059.0, "output_tokens_mean": 91.333, "latency_ms_mean": 1809.267, "usd_sum": 0.113205 } }, { "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": "[\"STRUCT_SWEET_OFFSET\",\"AROMA_SHARED_HERBAL\",\"REFRESH_ACID\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2065, "output_tokens": 85, "latency_ms": 2141.5, "usd": 0.03735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"AROMA_SHARED_HERBAL\",\"CONTRAST_SWEET_ACID\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2065, "output_tokens": 84, "latency_ms": 2193.0, "usd": 0.037275, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"AROMA_SHARED_HERBAL\",\"REFRESH_ACID\",\"CONTRAST_SWEET_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_HERBAL", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2065, "output_tokens": 84, "latency_ms": 1791.1, "usd": 0.037275, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8889, "score_summary": { "mean": 0.8889, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.8889, "ci95_hi": 0.8889, "n": 3 }, "score_if_valid": 0.8889, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2065.0, "output_tokens_mean": 84.333, "latency_ms_mean": 2041.867, "usd_sum": 0.1119 } }, { "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": "[\"HARMONY_REGIONAL\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\",\"AROMA_SHARED_EARTH\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 2044, "output_tokens": 82, "latency_ms": 1883.6, "usd": 0.03681, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"HARMONY_REGIONAL\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_MINERAL\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.8, "detail": { "predicted": [ "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.8, "recall": 0.8 }, "metrics": { "input_tokens": 2044, "output_tokens": 79, "latency_ms": 1716.1, "usd": 0.036585, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"HARMONY_REGIONAL\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\",\"REFRESH_MINERAL\",\"AROMA_SHARED_EARTH\"]", "compliant": true, "score": 0.6, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "precision": 0.6, "recall": 0.6 }, "metrics": { "input_tokens": 2044, "output_tokens": 75, "latency_ms": 2604.3, "usd": 0.036285, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.1155, "sem": 0.0667, "ci95_lo": 0.536, "ci95_hi": 0.7973, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2044.0, "output_tokens_mean": 78.667, "latency_ms_mean": 2068.0, "usd_sum": 0.10968 } }, { "task_id": "ogs:core:benchmark-task:xplain-011", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "mexican", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "1dfeb782059a4814", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"tacos al pastor with pineapple and chili\",\n \"beverage\": \"dry sparkling rosé (Cava rosado)\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "REFRESH_EFFERVESCE", "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP" ] }, "samples": [ { "sample": 0, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_SWEET_ACID\",\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\",\"STRUCT_SWEET_OFFSET\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2062, "output_tokens": 81, "latency_ms": 1673.7, "usd": 0.037005, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_RICH_CRISP\",\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\",\"STRUCT_SWEET_OFFSET\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2062, "output_tokens": 81, "latency_ms": 1708.7, "usd": 0.037005, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"AROMA_SHARED_FRUIT\",\"CONTRAST_SWEET_ACID\",\"REFRESH_EFFERVESCE\",\"REFRESH_ACID\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_ACID", "REFRESH_ACID", "REFRESH_EFFERVESCE", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FRUIT", "CONTRAST_RICH_CRISP", "REFRESH_EFFERVESCE", "STRUCT_SWEET_OFFSET" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 2062, "output_tokens": 82, "latency_ms": 6028.1, "usd": 0.03708, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.2223, "sem": 0.1283, "ci95_lo": 0.4152, "ci95_hi": 0.9182, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2062.0, "output_tokens_mean": 81.333, "latency_ms_mean": 3136.833, "usd_sum": 0.11109 } }, { "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": "[\"STRUCT_BODY_ALIGN\",\"STRUCT_TANNIN_FAT\",\"AROMA_SHARED_EARTH\",\"HARMONY_REGIONAL\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2059, "output_tokens": 87, "latency_ms": 4987.7, "usd": 0.03741, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_BODY_ALIGN\",\"STRUCT_TANNIN_FAT\",\"AROMA_SHARED_EARTH\",\"HARMONY_REGIONAL\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2059, "output_tokens": 87, "latency_ms": 2178.4, "usd": 0.03741, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"STRUCT_TANNIN_FAT\",\"AROMA_SHARED_EARTH\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_EARTH", "HARMONY_COMPLEXITY_MATCH", "HARMONY_REGIONAL", "STRUCT_TANNIN_FAT" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2059, "output_tokens": 92, "latency_ms": 6844.5, "usd": 0.037785, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8148, "score_summary": { "mean": 0.8148, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.6697, "ci95_hi": 0.96, "n": 3 }, "score_if_valid": 0.8148, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2059.0, "output_tokens_mean": 88.667, "latency_ms_mean": 4670.2, "usd_sum": 0.112605 } }, { "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": "[\"HARMONY_REGIONAL\",\"STRUCT_UMAMI_ENHANCE\",\"REFRESH_ACID\",\"AROMA_SHARED_EARTH\",\"CONTRAST_RICH_CRISP\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 2064, "output_tokens": 80, "latency_ms": 2855.7, "usd": 0.03696, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"HARMONY_REGIONAL\",\"CONTRAST_SWEET_SALTY\",\"REFRESH_ACID\",\"STRUCT_UMAMI_ENHANCE\",\"AROMA_SHARED_EARTH\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 2064, "output_tokens": 81, "latency_ms": 2758.2, "usd": 0.037035, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"HARMONY_REGIONAL\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_UMAMI_ENHANCE\",\"AROMA_SHARED_EARTH\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_EARTH", "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_SAVORY", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 2064, "output_tokens": 81, "latency_ms": 6327.5, "usd": 0.037035, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.4444, "score_summary": { "mean": 0.4444, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.4444, "ci95_hi": 0.4444, "n": 3 }, "score_if_valid": 0.4444, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2064.0, "output_tokens_mean": 80.667, "latency_ms_mean": 3980.467, "usd_sum": 0.11103 } }, { "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": "[\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_UMAMI_ENHANCE\",\"AROMA_SHARED_FRUIT\",\"STRUCT_BODY_ALIGN\",\"STRUCT_SWEET_OFFSET\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2067, "output_tokens": 94, "latency_ms": 1919.8, "usd": 0.038055, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"AROMA_SHARED_FRUIT\",\"STRUCT_UMAMI_ENHANCE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2067, "output_tokens": 95, "latency_ms": 5224.9, "usd": 0.03813, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_UMAMI_ENHANCE\",\"AROMA_SHARED_FRUIT\",\"STRUCT_INTENSITY_MATCH\",\"CONTRAST_SWEET_ACID\"]", "compliant": true, "score": 0.4444, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_FRUIT", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.4, "recall": 0.5 }, "metrics": { "input_tokens": 2067, "output_tokens": 95, "latency_ms": 4416.7, "usd": 0.03813, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.6667, "score_summary": { "mean": 0.6667, "stdev": 0.2223, "sem": 0.1283, "ci95_lo": 0.4152, "ci95_hi": 0.9182, "n": 3 }, "score_if_valid": 0.6667, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2067.0, "output_tokens_mean": 94.667, "latency_ms_mean": 3853.8, "usd_sum": 0.114315 } }, { "task_id": "ogs:core:benchmark-task:xplain-015", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "easy", "cuisine_region": "british", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "5474f731e5d9751c", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"Stilton blue cheese\",\n \"beverage\": \"Vintage Port\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "CONTRAST_SWEET_SALTY", "STRUCT_INTENSITY_MATCH", "HARMONY_COMPLEXITY_MATCH", "STRUCT_SWEET_OFFSET" ] }, "samples": [ { "sample": 0, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2045, "output_tokens": 95, "latency_ms": 2331.8, "usd": 0.0378, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"HARMONY_COMPLEXITY_MATCH\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2045, "output_tokens": 95, "latency_ms": 6319.3, "usd": 0.0378, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_COMPLEXITY_MATCH", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2045, "output_tokens": 88, "latency_ms": 1858.5, "usd": 0.037275, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8148, "score_summary": { "mean": 0.8148, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.6697, "ci95_hi": 0.96, "n": 3 }, "score_if_valid": 0.8148, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2045.0, "output_tokens_mean": 92.667, "latency_ms_mean": 3503.2, "usd_sum": 0.112875 } }, { "task_id": "ogs:core:benchmark-task:xplain-016", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "hard", "cuisine_region": "japanese", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "fc7f227aebed6756", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"shrimp tempura, light fry\",\n \"beverage\": \"chilled junmai ginjo sake\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_UMAMI_ENHANCE", "REFRESH_MINERAL", "AROMA_SHARED_FLORAL", "STRUCT_INTENSITY_MATCH", "HARMONY_REGIONAL" ] }, "samples": [ { "sample": 0, "raw_response": "[\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"CONTRAST_RICH_CRISP\",\"REFRESH_ACID\",\"HARMONY_REGIONAL\"]", "compliant": true, "score": 0.4, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.4 }, "metrics": { "input_tokens": 2053, "output_tokens": 80, "latency_ms": 6252.3, "usd": 0.036795, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"HARMONY_REGIONAL\",\"HARMONY_TEXTURE_MATCH\",\"CONTRAST_RICH_CRISP\"]", "compliant": true, "score": 0.4, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "HARMONY_TEXTURE_MATCH", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.4 }, "metrics": { "input_tokens": 2053, "output_tokens": 88, "latency_ms": 2615.9, "usd": 0.037395, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"STRUCT_INTENSITY_MATCH\",\"STRUCT_BODY_ALIGN\",\"HARMONY_REGIONAL\",\"CONTRAST_RICH_CRISP\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.4, "detail": { "predicted": [ "CONTRAST_RICH_CRISP", "HARMONY_REGIONAL", "REFRESH_ACID", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH" ], "expected": [ "AROMA_SHARED_FLORAL", "HARMONY_REGIONAL", "REFRESH_MINERAL", "STRUCT_INTENSITY_MATCH", "STRUCT_UMAMI_ENHANCE" ], "precision": 0.4, "recall": 0.4 }, "metrics": { "input_tokens": 2053, "output_tokens": 80, "latency_ms": 5024.8, "usd": 0.036795, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.4, "score_summary": { "mean": 0.4, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.4, "ci95_hi": 0.4, "n": 3 }, "score_if_valid": 0.4, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2053.0, "output_tokens_mean": 82.667, "latency_ms_mean": 4631.0, "usd_sum": 0.110985 } }, { "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": "[\"HARMONY_REGIONAL\",\"REFRESH_ACID\",\"AROMA_SHARED_HERBAL\",\"REFRESH_MINERAL\",\"STRUCT_ACIDITY_BALANCE\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2062, "output_tokens": 77, "latency_ms": 2048.2, "usd": 0.036705, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"HARMONY_REGIONAL\",\"AROMA_SHARED_HERBAL\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\",\"REFRESH_MINERAL\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2062, "output_tokens": 77, "latency_ms": 6127.6, "usd": 0.036705, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"HARMONY_REGIONAL\",\"REFRESH_ACID\",\"AROMA_SHARED_HERBAL\",\"REFRESH_MINERAL\",\"STRUCT_ACIDITY_BALANCE\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL", "STRUCT_ACIDITY_BALANCE" ], "expected": [ "AROMA_SHARED_HERBAL", "HARMONY_REGIONAL", "REFRESH_ACID", "REFRESH_MINERAL" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2062, "output_tokens": 77, "latency_ms": 1821.2, "usd": 0.036705, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8889, "score_summary": { "mean": 0.8889, "stdev": 0.0, "sem": 0.0, "ci95_lo": 0.8889, "ci95_hi": 0.8889, "n": 3 }, "score_if_valid": 0.8889, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2062.0, "output_tokens_mean": 77.0, "latency_ms_mean": 3332.333, "usd_sum": 0.110115 } }, { "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": "[\"STRUCT_SWEET_OFFSET\",\"CONTRAST_SWEET_SALTY\",\"REFRESH_ACID\",\"AROMA_SHARED_FRUIT\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_INTENSITY_MATCH", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2065, "output_tokens": 85, "latency_ms": 8768.4, "usd": 0.03735, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"CONTRAST_SWEET_SALTY\",\"REFRESH_ACID\",\"STRUCT_ACIDITY_BALANCE\",\"AROMA_SHARED_FRUIT\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_ACIDITY_BALANCE", "STRUCT_SWEET_OFFSET" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2065, "output_tokens": 86, "latency_ms": 1925.1, "usd": 0.037425, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"CONTRAST_SWEET_SALTY\",\"REFRESH_ACID\",\"STRUCT_TANNIN_FAT\",\"AROMA_SHARED_FRUIT\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "AROMA_SHARED_FRUIT", "CONTRAST_SWEET_SALTY", "REFRESH_ACID", "STRUCT_SWEET_OFFSET", "STRUCT_TANNIN_FAT" ], "expected": [ "AROMA_SHARED_FRUIT", "HARMONY_COMPLEXITY_MATCH", "REFRESH_ACID", "STRUCT_SWEET_OFFSET" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2065, "output_tokens": 83, "latency_ms": 1662.3, "usd": 0.0372, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 2065.0, "output_tokens_mean": 84.667, "latency_ms_mean": 4118.6, "usd_sum": 0.111975 } }, { "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": "[\"HARMONY_REGIONAL\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_UMAMI_ENHANCE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2067, "output_tokens": 92, "latency_ms": 6369.7, "usd": 0.037905, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"HARMONY_REGIONAL\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_TANNIN_FAT\",\"STRUCT_BODY_ALIGN\",\"STRUCT_INTENSITY_MATCH\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_FAT", "STRUCT_TANNIN_PROTEIN" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2067, "output_tokens": 89, "latency_ms": 4142.8, "usd": 0.03768, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"HARMONY_REGIONAL\",\"STRUCT_BODY_ALIGN\",\"STRUCT_TANNIN_PROTEIN\",\"STRUCT_INTENSITY_MATCH\",\"STRUCT_UMAMI_ENHANCE\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_INTENSITY_MATCH", "STRUCT_TANNIN_PROTEIN", "STRUCT_UMAMI_ENHANCE" ], "expected": [ "AROMA_SHARED_WOOD", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_TANNIN_PROTEIN" ], "precision": 0.6, "recall": 0.75 }, "metrics": { "input_tokens": 2067, "output_tokens": 92, "latency_ms": 2519.7, "usd": 0.037905, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "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": 2067.0, "output_tokens_mean": 91.0, "latency_ms_mean": 4344.067, "usd_sum": 0.11349 } }, { "task_id": "ogs:core:benchmark-task:xplain-020", "category": "explanation", "capability": "explanation_code_selection", "difficulty": "easy", "cuisine_region": "french", "scorer": "set_f1", "context_needs": [ "vocab.explanation_codes.positive" ], "prompt_template_hash": "43005f44c870684b", "prompt": "You are a gastronomy expert evaluated by the Open Gastronomy Standard (OGS) Benchmark.\n\nYou will be given:\n- The relevant slices of the OGS specification (controlled vocabularies, scales,\n JSON schemas) needed to answer the task correctly.\n- A task instruction, an input payload, and an answer format.\n\nFollow these rules:\n- Use ONLY the OGS controlled vocabularies supplied below. Do not invent new\n enum values, tag names, or code IDs.\n- When the task asks for JSON, respond with a single JSON document and nothing\n else. Do NOT wrap JSON in markdown code fences.\n- When the task asks for a single token (e.g. 'a', '3', 'fruit'), respond with\n just the token and no surrounding prose.\n- Intensities use the OGS 0-10 scale unless otherwise stated\n (0 = not detectable, 10 = overwhelming).\n- If the task supplies a list of candidates, your answer must come from that\n list exactly.\n\n## OGS Context\n\n### OGS Explanation Codes (positive only)\n\nEach code has a fixed `id` (UPPER_SNAKE_CASE). Use the exact `id` string.\n\n**aromatic_bridge**\n- `AROMA_SHARED_FRUIT` — Shared Fruit Aromatics: Both dish and beverage share fruit aromatic families, creating an aromatic bridge.\n- `AROMA_SHARED_SPICE` — Shared Spice Notes: Spice aromatics appear in both dish and beverage, linking them aromatically.\n- `AROMA_SHARED_EARTH` — Shared Earth Notes: Earthy, mineral, or fungal aromatics bridge the dish and beverage.\n- `AROMA_SHARED_HERBAL` — Shared Herbal Notes: Herbal aromatics present in both dish and beverage create continuity.\n- `AROMA_SHARED_FLORAL` — Shared Floral Notes: Floral aromatics appear in both elements, creating an elegant aromatic link.\n- `AROMA_SHARED_WOOD` — Shared Wood/Oak Notes: Wood, smoke, or oak aromatics bridge dish and beverage (e.g., grilled meat with oaked wine).\n\n**contrast**\n- `CONTRAST_SWEET_ACID` — Sweet-Acid Contrast: Sweetness in one element contrasts with acidity in the other, creating dynamic tension.\n- `CONTRAST_RICH_CRISP` — Rich-Crisp Contrast: A rich, heavy dish is contrasted by a crisp, lean beverage (or vice versa).\n- `CONTRAST_SWEET_SALTY` — Sweet-Salty Contrast: Sweetness in the beverage contrasts with saltiness in the dish, creating interest.\n- `CONTRAST_TEMP_TEXTURE` — Temperature-Texture Contrast: Temperature or textural differences between dish and beverage create pleasant contrast.\n\n**harmony**\n- `HARMONY_FLAVOR_CONVERGE` — Flavor Profile Convergence: The overall flavor profiles of dish and beverage converge, creating a unified taste experience.\n- `HARMONY_TEXTURE_MATCH` — Textural Harmony: The textures of dish and beverage complement each other harmoniously.\n- `HARMONY_REGIONAL` — Regional Affinity: Dish and beverage share a regional origin, reflecting terroir-driven compatibility.\n- `HARMONY_COMPLEXITY_MATCH` — Complexity Match: Both dish and beverage have similar complexity levels, so neither outshines the other.\n\n**positive_structural**\n- `STRUCT_INTENSITY_MATCH` — Intensity Match: The overall flavor intensity of the dish and beverage are well-aligned, so neither overpowers the other.\n- `STRUCT_BODY_ALIGN` — Body Alignment: The body/weight of the dish matches the body of the beverage, creating a balanced mouthfeel.\n- `STRUCT_ACIDITY_BALANCE` — Acidity Balance: The beverage's acidity cuts through richness or matches the dish's acidity, creating freshness.\n- `STRUCT_TANNIN_FAT` — Tannin-Fat Synergy: Tannins in the beverage are softened by fat in the dish, creating a smooth, integrated sensation.\n- `STRUCT_TANNIN_PROTEIN` — Tannin-Protein Synergy: Proteins in the dish bind with tannins, reducing astringency and enhancing mouthfeel.\n- `STRUCT_SWEET_OFFSET` — Sweetness Offset: Residual sweetness in the beverage balances salt, spice, or acidity in the dish.\n- `STRUCT_UMAMI_ENHANCE` — Umami Enhancement: Umami in the dish enhances the perceived fruit and body of the beverage.\n- `STRUCT_ALCOHOL_WARMTH` — Alcohol Warmth Complement: The warmth of alcohol complements rich, hearty dishes without overpowering.\n\n**refresh**\n- `REFRESH_EFFERVESCE` — Effervescence Cleanse: Carbonation in the beverage physically scrubs the palate between bites of rich food.\n- `REFRESH_ACID` — Acid Refresh: High acidity in the beverage refreshes the palate, cutting through fat and richness.\n- `REFRESH_MINERAL` — Mineral Reset: Mineral character in the beverage provides a clean, palate-resetting effect.\n\n---\n\nReturn the OGS positive explanation codes that best explain why the pairing below works. Respond as a JSON array of code IDs (3 to 5 codes).\n\nINPUT:\n{\n \"dish\": \"foie gras torchon with brioche\",\n \"beverage\": \"Sauternes\"\n}\n\nANSWER FORMAT: set_of_codes", "expected": { "values": [ "STRUCT_SWEET_OFFSET", "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN" ] }, "samples": [ { "sample": 0, "raw_response": "[\"CONTRAST_SWEET_SALTY\",\"STRUCT_SWEET_OFFSET\",\"STRUCT_BODY_ALIGN\",\"HARMONY_REGIONAL\",\"STRUCT_ACIDITY_BALANCE\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2046, "output_tokens": 89, "latency_ms": 6123.3, "usd": 0.037365, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 1, "raw_response": "[\"STRUCT_SWEET_OFFSET\",\"CONTRAST_SWEET_SALTY\",\"STRUCT_ACIDITY_BALANCE\",\"HARMONY_REGIONAL\",\"STRUCT_BODY_ALIGN\"]", "compliant": true, "score": 0.8889, "detail": { "predicted": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_ACIDITY_BALANCE", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "expected": [ "CONTRAST_SWEET_SALTY", "HARMONY_REGIONAL", "STRUCT_BODY_ALIGN", "STRUCT_SWEET_OFFSET" ], "precision": 0.8, "recall": 1.0 }, "metrics": { "input_tokens": 2046, "output_tokens": 89, "latency_ms": 2041.5, "usd": 0.037365, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } }, { "sample": 2, "raw_response": "[\"CONTRAST_SWEET_ACID\",\"STRUCT_SWEET_OFFSET\",\"HARMONY_REGIONAL\",\"STRUCT_BODY_ALIGN\",\"REFRESH_ACID\"]", "compliant": true, "score": 0.6667, "detail": { "predicted": [ "CONTRAST_SWEET_ACID", "HARMONY_REGIONAL", "REFRESH_ACID", "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": 2046, "output_tokens": 79, "latency_ms": 9717.5, "usd": 0.036615, "model_version": "claude-opus-4-7", "finish_reason": "end_turn" } } ], "score": 0.8148, "score_summary": { "mean": 0.8148, "stdev": 0.1283, "sem": 0.0741, "ci95_lo": 0.6697, "ci95_hi": 0.96, "n": 3 }, "score_if_valid": 0.8148, "format_rate": 1.0, "metrics": { "input_tokens_mean": 2046.0, "output_tokens_mean": 85.667, "latency_ms_mean": 5960.767, "usd_sum": 0.111345 } } ], "category_scores": { "composition": { "mean_score": 0.8866, "ci95_lo": 0.7512, "ci95_hi": 1.0221, "stdev": 0.309, "task_count": 20, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.8866 }, "dietary": { "mean_score": 0.8889, "ci95_lo": 0.7215, "ci95_hi": 1.0563, "stdev": 0.2959, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.8889 }, "explanation": { "mean_score": 0.728, "ci95_lo": 0.6663, "ci95_hi": 0.7897, "stdev": 0.1408, "task_count": 20, "weight": 0.1, "format_rate": 1.0, "score_if_valid": 0.728 }, "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": 0.6461, "ci95_lo": 0.3523, "ci95_hi": 0.9399, "stdev": 0.474, "task_count": 10, "weight": 0.03, "format_rate": 1.0, "score_if_valid": 0.6461 }, "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": 0.9583, "ci95_lo": 0.8767, "ci95_hi": 1.04, "stdev": 0.2041, "task_count": 24, "weight": 0.05, "format_rate": 1.0, "score_if_valid": 0.9583 }, "risk": { "mean_score": 0.85, "ci95_lo": 0.6894, "ci95_hi": 1.0106, "stdev": 0.3663, "task_count": 20, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 0.85 }, "safety": { "mean_score": 0.9861, "ci95_lo": 0.9589, "ci95_hi": 1.0133, "stdev": 0.0481, "task_count": 12, "weight": 0.06, "format_rate": 1.0, "score_if_valid": 0.9861 }, "sensory": { "mean_score": 0.6631, "ci95_lo": 0.5411, "ci95_hi": 0.7851, "stdev": 0.2852, "task_count": 21, "weight": 0.12, "format_rate": 1.0, "score_if_valid": 0.6631 }, "structured_output": { "mean_score": 0.7667, "ci95_lo": 0.5951, "ci95_hi": 0.9382, "stdev": 0.3914, "task_count": 20, "weight": 0.12, "format_rate": 0.9167, "score_if_valid": 0.7667 }, "vocabulary": { "mean_score": 1.0, "ci95_lo": 1.0, "ci95_hi": 1.0, "stdev": 0.0, "task_count": 23, "weight": 0.08, "format_rate": 1.0, "score_if_valid": 1.0 } }, "aggregate": { "score": 85.86, "ci95_lo": 82.25, "ci95_hi": 89.47, "scale": "0-100", "partial": false, "missing_categories": [] }, "metrics": { "latency_ms_mean": 2456.901, "latency_ms_median": 1350.0, "input_tokens_mean": 1181.0, "output_tokens_mean": 92.1, "usd_total": 15.732465, "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)." } }