{ "dataset": "Clinical Benchmarks", "kind": "index", "url": "https://clinicalbenchmarks.ai", "updated": "2026-09-30", "revision": 7165, "licence": { "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "attribution": "Clinical Benchmarks (clinicalbenchmarks.ai)", "note": "The compilation is licensed CC BY 4.0. Source documents keep their own terms." }, "rule": "Each board ranks only its own rows. Scores from different benchmarks are combined only in this site's own index (/api/v1/index.json), which is labelled as such.", "data": { "name": "Clinical Benchmarks Index", "note": "This site's own calculation from its boards. Each board still ranks only its own rows.", "methodology": "https://clinicalbenchmarks.ai/methodology#index", "method": { "scale": "0 to 100", "perBoard": "a model's best headline result, placed between the lowest and highest such result on that board", "aggregate": "mean over the boards the model has results on, times a confidence multiplier", "confidence": "full from 3 boards; below that the square root of boards / 3 (2 boards x0.816, 1 board x0.577)", "fullBoards": 3, "minBoards": 1, "minBoardModels": 5, "excludes": "harness plus model pairings, products, research systems, human and baseline references" }, "boards": [ { "id": "healthbench-professional", "name": "HealthBench Professional", "shortName": null, "used": true, "models": 26, "low": 0.35, "high": 0.703 }, { "id": "medscribe", "name": "MedScribe (Vals AI)", "shortName": null, "used": true, "models": 94, "low": 4.27, "high": 91.43 }, { "id": "medcode", "name": "MedCode (Vals AI)", "shortName": null, "used": true, "models": 94, "low": 19.72, "high": 63.57 }, { "id": "medpic-bench", "name": "MedPIC-Bench", "shortName": "MedPIC", "used": true, "models": 28, "low": 36, "high": 80.7 }, { "id": "medxpertqa-mm", "name": "MedXpertQA (MM)", "shortName": null, "used": true, "models": 22, "low": 23.5, "high": 81.5 }, { "id": "mast", "name": "MAST (Medical AI Superintelligence Test)", "shortName": null, "used": true, "models": 8, "low": 53.7, "high": 60.2 }, { "id": "medhelm", "name": "MedHELM", "shortName": null, "used": true, "models": 10, "low": 0.342, "high": 0.652 }, { "id": "first-do-noharm", "name": "First, Do NOHARM (v2)", "shortName": null, "used": true, "models": 13, "low": 55.8, "high": 79.7 }, { "id": "physicianbench", "name": "PhysicianBench", "shortName": null, "used": true, "models": 17, "low": 5.3, "high": 68.4 }, { "id": "ehr-complex", "name": "EHR-Complex", "shortName": null, "used": true, "models": 17, "low": 0.16, "high": 0.65 }, { "id": "healthagentbench", "name": "HealthAgentBench", "shortName": null, "used": false, "models": 0, "low": null, "high": null }, { "id": "chi-bench", "name": "CHI-Bench", "shortName": null, "used": false, "models": 0, "low": null, "high": null }, { "id": "healthadminbench", "name": "HealthAdminBench", "shortName": null, "used": false, "models": 3, "low": null, "high": null } ], "entries": [ { "model": "claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "lab": "anthropic", "score": 91, "raw": 91, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1800, "valueLabel": "0.692", "normalized": 96.9 }, { "benchmark": "medscribe", "result": 2152, "valueLabel": "91.10", "normalized": 99.6 }, { "benchmark": "medcode", "result": 1967, "valueLabel": "52.92", "normalized": 75.7 }, { "benchmark": "physicianbench", "result": 1831, "valueLabel": "63.2", "normalized": 91.8 } ], "rank": 1, "url": "https://clinicalbenchmarks.ai/models/claude-sonnet-5.5" }, { "model": "claude-opus-5.5", "name": "Claude Opus 5.5", "lab": "anthropic", "score": 88.8, "raw": 88.8, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1801, "valueLabel": "0.656", "normalized": 86.7 }, { "benchmark": "medscribe", "result": 2151, "valueLabel": "91.43", "normalized": 100 }, { "benchmark": "medcode", "result": 1971, "valueLabel": "49.80", "normalized": 68.6 }, { "benchmark": "physicianbench", "result": 1830, "valueLabel": "68.4", "normalized": 100 } ], "rank": 2, "url": "https://clinicalbenchmarks.ai/models/claude-opus-5.5" }, { "model": "muse-spark-1.1", "name": "Muse Spark 1.1", "lab": "meta", "score": 88.6, "raw": 88.6, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 505, "valueLabel": "0.593", "normalized": 68.8 }, { "benchmark": "medscribe", "result": 356, "valueLabel": "88.89", "normalized": 97.1 }, { "benchmark": "first-do-noharm", "result": 288, "valueLabel": "79.7", "normalized": 100 } ], "rank": 3, "url": "https://clinicalbenchmarks.ai/models/muse-spark-1.1" }, { "model": "gemini-3.5-flash", "name": "Gemini 3.5 Flash", "lab": "google", "score": 87.4, "raw": 87.4, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2209, "valueLabel": "76.57", "normalized": 83 }, { "benchmark": "medcode", "result": 149, "valueLabel": "55.83", "normalized": 82.3 }, { "benchmark": "medhelm", "result": 115, "valueLabel": "0.642", "normalized": 96.8 } ], "rank": 4, "url": "https://clinicalbenchmarks.ai/models/gemini-3.5-flash" }, { "model": "gpt-6-astra", "name": "GPT-6 Astra", "lab": "openai", "score": 87.2, "raw": 87.2, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1799, "valueLabel": "0.703", "normalized": 100 }, { "benchmark": "medscribe", "result": 567, "valueLabel": "87.91", "normalized": 96 }, { "benchmark": "medcode", "result": 568, "valueLabel": "48.49", "normalized": 65.6 } ], "rank": 5, "url": "https://clinicalbenchmarks.ai/models/gpt-6-astra" }, { "model": "claude-fable-5.1", "name": "Claude Fable 5.1", "lab": "anthropic", "score": 85.5, "raw": 85.5, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 561, "valueLabel": "0.621", "normalized": 76.8 }, { "benchmark": "medscribe", "result": 354, "valueLabel": "91.29", "normalized": 99.8 }, { "benchmark": "medcode", "result": 348, "valueLabel": "53.51", "normalized": 77.1 }, { "benchmark": "physicianbench", "result": 1832, "valueLabel": "61.0", "normalized": 88.3 } ], "rank": 6, "url": "https://clinicalbenchmarks.ai/models/claude-fable-5.1" }, { "model": "kimi-k3", "name": "Kimi K3", "lab": "moonshot", "score": 84.3, "raw": 84.3, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "medscribe", "result": 359, "valueLabel": "87.96", "normalized": 96 }, { "benchmark": "medcode", "result": 1979, "valueLabel": "48.88", "normalized": 66.5 }, { "benchmark": "mast", "result": 107, "valueLabel": "60.1", "normalized": 98.5 }, { "benchmark": "first-do-noharm", "result": 125, "valueLabel": "74.0", "normalized": 76.2 } ], "rank": 7, "url": "https://clinicalbenchmarks.ai/models/kimi-k3" }, { "model": "gemini-3.6-flash", "name": "Gemini 3.6 Flash", "lab": "google", "score": 83, "raw": 83, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2196, "valueLabel": "79.66", "normalized": 86.5 }, { "benchmark": "medcode", "result": 352, "valueLabel": "53.15", "normalized": 76.2 }, { "benchmark": "mast", "result": 108, "valueLabel": "59.3", "normalized": 86.2 } ], "rank": 8, "url": "https://clinicalbenchmarks.ai/models/gemini-3.6-flash" }, { "model": "muse-spark", "name": "Muse Spark", "lab": "meta", "score": 80.9, "raw": 80.9, "confidence": 1, "boards": 5, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 506, "valueLabel": "0.541", "normalized": 54.1 }, { "benchmark": "medscribe", "result": 2160, "valueLabel": "85.90", "normalized": 93.7 }, { "benchmark": "medcode", "result": 1969, "valueLabel": "51.31", "normalized": 72 }, { "benchmark": "medxpertqa-mm", "result": 158, "valueLabel": "78.4", "normalized": 94.7 }, { "benchmark": "medhelm", "result": 116, "valueLabel": "0.621", "normalized": 90 } ], "rank": 9, "url": "https://clinicalbenchmarks.ai/models/muse-spark" }, { "model": "claude-fable-5", "name": "Claude Fable 5", "lab": "anthropic", "score": 80.7, "raw": 80.7, "confidence": 1, "boards": 5, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 204, "valueLabel": "0.660", "normalized": 87.8 }, { "benchmark": "medscribe", "result": 357, "valueLabel": "88.52", "normalized": 96.7 }, { "benchmark": "medcode", "result": 147, "valueLabel": "56.07", "normalized": 82.9 }, { "benchmark": "medxpertqa-mm", "result": 547, "valueLabel": "80.0", "normalized": 97.4 }, { "benchmark": "first-do-noharm", "result": 289, "valueLabel": "65.0", "normalized": 38.5 } ], "rank": 10, "url": "https://clinicalbenchmarks.ai/models/claude-fable-5" }, { "model": "claude-opus-5", "name": "Claude Opus 5", "lab": "anthropic", "score": 80.6, "raw": 80.6, "confidence": 1, "boards": 6, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 206, "valueLabel": "0.598", "normalized": 70.3 }, { "benchmark": "medscribe", "result": 150, "valueLabel": "90.98", "normalized": 99.5 }, { "benchmark": "medcode", "result": 145, "valueLabel": "63.57", "normalized": 100 }, { "benchmark": "mast", "result": 111, "valueLabel": "57.1", "normalized": 52.3 }, { "benchmark": "first-do-noharm", "result": 124, "valueLabel": "74.6", "normalized": 78.7 }, { "benchmark": "physicianbench", "result": 1833, "valueLabel": "57.6", "normalized": 82.9 } ], "rank": 11, "url": "https://clinicalbenchmarks.ai/models/claude-opus-5" }, { "model": "gpt-5.6-sol", "name": "GPT-5.6 Sol", "lab": "openai", "score": 80, "raw": 80, "confidence": 1, "boards": 6, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 205, "valueLabel": "0.605", "normalized": 72.2 }, { "benchmark": "medscribe", "result": 2166, "valueLabel": "85.23", "normalized": 92.9 }, { "benchmark": "medcode", "result": 1994, "valueLabel": "43.97", "normalized": 55.3 }, { "benchmark": "medxpertqa-mm", "result": 548, "valueLabel": "81.5", "normalized": 100 }, { "benchmark": "mast", "result": 106, "valueLabel": "60.2", "normalized": 100 }, { "benchmark": "first-do-noharm", "result": 126, "valueLabel": "70.1", "normalized": 59.8 } ], "rank": 12, "url": "https://clinicalbenchmarks.ai/models/gpt-5.6-sol" }, { "model": "qwen3.8-max", "name": "Qwen3.8 Max", "lab": "alibaba", "score": 79.5, "raw": 79.5, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2168, "valueLabel": "84.95", "normalized": 92.6 }, { "benchmark": "medcode", "result": 2012, "valueLabel": "40.67", "normalized": 47.8 }, { "benchmark": "medxpertqa-mm", "result": 157, "valueLabel": "80.4", "normalized": 98.1 } ], "rank": 13, "url": "https://clinicalbenchmarks.ai/models/qwen3.8-max" }, { "model": "claude-opus-4.8", "name": "Claude Opus 4.8", "lab": "anthropic", "score": 79.1, "raw": 79.1, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1871, "valueLabel": "0.574", "normalized": 63.5 }, { "benchmark": "medscribe", "result": 2161, "valueLabel": "85.75", "normalized": 93.5 }, { "benchmark": "medcode", "result": 350, "valueLabel": "53.22", "normalized": 76.4 }, { "benchmark": "medxpertqa-mm", "result": 546, "valueLabel": "71.7", "normalized": 83.1 } ], "rank": 14, "url": "https://clinicalbenchmarks.ai/models/claude-opus-4.8" }, { "model": "claude-opus-4.5", "name": "Claude Opus 4.5", "lab": "anthropic", "score": 76.4, "raw": 76.4, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2164, "valueLabel": "85.32", "normalized": 93 }, { "benchmark": "medcode", "result": 1976, "valueLabel": "49.16", "normalized": 67.1 }, { "benchmark": "medxpertqa-mm", "result": 1824, "valueLabel": "63.6", "normalized": 69.1 } ], "rank": 15, "url": "https://clinicalbenchmarks.ai/models/claude-opus-4.5" }, { "model": "grok-4.7", "name": "Grok 4.7", "lab": "xai", "score": 75.7, "raw": 75.7, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1804, "valueLabel": "0.567", "normalized": 61.5 }, { "benchmark": "medscribe", "result": 2153, "valueLabel": "89.38", "normalized": 97.6 }, { "benchmark": "medcode", "result": 1974, "valueLabel": "49.55", "normalized": 68 } ], "rank": 16, "url": "https://clinicalbenchmarks.ai/models/grok-4.7" }, { "model": "gemini-3.1-pro", "name": "Gemini 3.1 Pro", "lab": "google", "score": 75.3, "raw": 75.3, "confidence": 1, "boards": 9, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2211, "valueLabel": "76.11", "normalized": 82.4 }, { "benchmark": "medcode", "result": 146, "valueLabel": "59.06", "normalized": 89.7 }, { "benchmark": "medpic-bench", "result": 1567, "valueLabel": "80.7", "normalized": 100 }, { "benchmark": "medxpertqa-mm", "result": 156, "valueLabel": "81.3", "normalized": 99.7 }, { "benchmark": "mast", "result": 109, "valueLabel": "58.9", "normalized": 80 }, { "benchmark": "medhelm", "result": 114, "valueLabel": "0.652", "normalized": 100 }, { "benchmark": "first-do-noharm", "result": 128, "valueLabel": "62.6", "normalized": 28.5 }, { "benchmark": "physicianbench", "result": 174, "valueLabel": "6.0", "normalized": 1.1 }, { "benchmark": "ehr-complex", "result": 176, "valueLabel": "0.630", "normalized": 95.9 } ], "rank": 17, "url": "https://clinicalbenchmarks.ai/models/gemini-3.1-pro" }, { "model": "gpt-6-sol", "name": "GPT-6 Sol", "lab": "openai", "score": 74.9, "raw": 74.9, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1802, "valueLabel": "0.608", "normalized": 73.1 }, { "benchmark": "medscribe", "result": 2187, "valueLabel": "82.03", "normalized": 89.2 }, { "benchmark": "medcode", "result": 1987, "valueLabel": "47.07", "normalized": 62.4 } ], "rank": 18, "url": "https://clinicalbenchmarks.ai/models/gpt-6-sol" }, { "model": "gpt-6-luna", "name": "GPT-6 Luna", "lab": "openai", "score": 73.7, "raw": 73.7, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1803, "valueLabel": "0.608", "normalized": 73.1 }, { "benchmark": "medscribe", "result": 2178, "valueLabel": "83.71", "normalized": 91.1 }, { "benchmark": "medcode", "result": 1992, "valueLabel": "44.69", "normalized": 56.9 } ], "rank": 19, "url": "https://clinicalbenchmarks.ai/models/gpt-6-luna" }, { "model": "kimi-k2.5", "name": "Kimi K2.5", "lab": "moonshot", "score": 73.4, "raw": 73.4, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2210, "valueLabel": "76.44", "normalized": 82.8 }, { "benchmark": "medcode", "result": 2019, "valueLabel": "39.32", "normalized": 44.7 }, { "benchmark": "medxpertqa-mm", "result": 551, "valueLabel": "65.3", "normalized": 72.1 }, { "benchmark": "ehr-complex", "result": 177, "valueLabel": "0.620", "normalized": 93.9 } ], "rank": 20, "url": "https://clinicalbenchmarks.ai/models/kimi-k2.5" }, { "model": "gpt-5.2", "name": "GPT-5.2", "lab": "openai", "score": 69.8, "raw": 69.8, "confidence": 1, "boards": 5, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 487, "valueLabel": "0.459", "normalized": 30.9 }, { "benchmark": "medscribe", "result": 2172, "valueLabel": "84.39", "normalized": 91.9 }, { "benchmark": "medcode", "result": 1972, "valueLabel": "49.75", "normalized": 68.5 }, { "benchmark": "medpic-bench", "result": 1539, "valueLabel": "68.1", "normalized": 71.8 }, { "benchmark": "medxpertqa-mm", "result": 550, "valueLabel": "73.3", "normalized": 85.9 } ], "rank": 21, "url": "https://clinicalbenchmarks.ai/models/gpt-5.2" }, { "model": "gpt-5.6-terra", "name": "GPT-5.6 Terra", "lab": "openai", "score": 69.5, "raw": 69.5, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 208, "valueLabel": "0.577", "normalized": 64.3 }, { "benchmark": "medscribe", "result": 2186, "valueLabel": "82.87", "normalized": 90.2 }, { "benchmark": "medcode", "result": 1996, "valueLabel": "43.41", "normalized": 54 } ], "rank": 22, "url": "https://clinicalbenchmarks.ai/models/gpt-5.6-terra" }, { "model": "gemini-3-pro", "name": "Gemini 3 Pro", "lab": "google", "score": 68.7, "raw": 84.2, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2225, "valueLabel": "72.04", "normalized": 77.8 }, { "benchmark": "medxpertqa-mm", "result": 1823, "valueLabel": "76.0", "normalized": 90.5 } ], "rank": 23, "url": "https://clinicalbenchmarks.ai/models/gemini-3-pro" }, { "model": "gemini-3.7-flash", "name": "Gemini 3.7 Flash", "lab": "google", "score": 68.6, "raw": 84.1, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2175, "valueLabel": "83.94", "normalized": 91.4 }, { "benchmark": "medcode", "result": 1966, "valueLabel": "53.39", "normalized": 76.8 } ], "rank": 24, "url": "https://clinicalbenchmarks.ai/models/gemini-3.7-flash" }, { "model": "muse-spark-1.2", "name": "Muse Spark 1.2", "lab": "meta", "score": 67.7, "raw": 83, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 355, "valueLabel": "90.06", "normalized": 98.4 }, { "benchmark": "medcode", "result": 1975, "valueLabel": "49.35", "normalized": 67.6 } ], "rank": 25, "url": "https://clinicalbenchmarks.ai/models/muse-spark-1.2" }, { "model": "gpt-5.6-luna", "name": "GPT-5.6 Luna", "lab": "openai", "score": 67.4, "raw": 67.4, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 210, "valueLabel": "0.557", "normalized": 58.6 }, { "benchmark": "medscribe", "result": 2171, "valueLabel": "84.39", "normalized": 91.9 }, { "benchmark": "medcode", "result": 2002, "valueLabel": "42.39", "normalized": 51.7 } ], "rank": 26, "url": "https://clinicalbenchmarks.ai/models/gpt-5.6-luna" }, { "model": "gpt-5.5", "name": "GPT-5.5", "lab": "openai", "score": 66.8, "raw": 66.8, "confidence": 1, "boards": 5, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 489, "valueLabel": "0.518", "normalized": 47.6 }, { "benchmark": "medscribe", "result": 361, "valueLabel": "86.87", "normalized": 94.8 }, { "benchmark": "medcode", "result": 1978, "valueLabel": "49.10", "normalized": 67 }, { "benchmark": "first-do-noharm", "result": 127, "valueLabel": "70.0", "normalized": 59.4 }, { "benchmark": "physicianbench", "result": 167, "valueLabel": "46.3", "normalized": 65 } ], "rank": 27, "url": "https://clinicalbenchmarks.ai/models/gpt-5.5" }, { "model": "gpt-5", "name": "GPT-5", "lab": "openai", "score": 66.6, "raw": 66.6, "confidence": 1, "boards": 5, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 485, "valueLabel": "0.462", "normalized": 31.7 }, { "benchmark": "medscribe", "result": 2179, "valueLabel": "83.65", "normalized": 91.1 }, { "benchmark": "medcode", "result": 1973, "valueLabel": "49.63", "normalized": 68.2 }, { "benchmark": "medpic-bench", "result": 1560, "valueLabel": "75.6", "normalized": 88.6 }, { "benchmark": "first-do-noharm", "result": 294, "valueLabel": "68.6", "normalized": 53.6 } ], "rank": 28, "url": "https://clinicalbenchmarks.ai/models/gpt-5" }, { "model": "gpt-5.4", "name": "GPT-5.4", "lab": "openai", "score": 65.9, "raw": 65.9, "confidence": 1, "boards": 7, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 488, "valueLabel": "0.481", "normalized": 37.1 }, { "benchmark": "medscribe", "result": 2203, "valueLabel": "77.55", "normalized": 84.1 }, { "benchmark": "medcode", "result": 2006, "valueLabel": "41.29", "normalized": 49.2 }, { "benchmark": "medxpertqa-mm", "result": 159, "valueLabel": "77.1", "normalized": 92.4 }, { "benchmark": "medhelm", "result": 118, "valueLabel": "0.538", "normalized": 63.2 }, { "benchmark": "physicianbench", "result": 170, "valueLabel": "27.7", "normalized": 35.5 }, { "benchmark": "ehr-complex", "result": 175, "valueLabel": "0.650", "normalized": 100 } ], "rank": 29, "url": "https://clinicalbenchmarks.ai/models/gpt-5.4" }, { "model": "gpt-6.1-sol", "name": "GPT-6.1 Sol", "lab": "openai", "score": 65.6, "raw": 80.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2158, "valueLabel": "86.45", "normalized": 94.3 }, { "benchmark": "medcode", "result": 1980, "valueLabel": "48.84", "normalized": 66.4 } ], "rank": 30, "url": "https://clinicalbenchmarks.ai/models/gpt-6.1-sol" }, { "model": "qwen3.5-397b-a17b", "name": "Qwen3.5 397B A17B", "lab": "alibaba", "score": 65.2, "raw": 65.2, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 552, "valueLabel": "70.0", "normalized": 80.2 }, { "benchmark": "mast", "result": 110, "valueLabel": "57.9", "normalized": 64.6 }, { "benchmark": "first-do-noharm", "result": 291, "valueLabel": "61.1", "normalized": 22.2 }, { "benchmark": "ehr-complex", "result": 178, "valueLabel": "0.620", "normalized": 93.9 } ], "rank": 31, "url": "https://clinicalbenchmarks.ai/models/qwen3.5-397b-a17b" }, { "model": "gemini-3-flash", "name": "Gemini 3 Flash", "lab": "google", "score": 64.4, "raw": 78.9, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2229, "valueLabel": "69.92", "normalized": 75.3 }, { "benchmark": "medcode", "result": 148, "valueLabel": "55.92", "normalized": 82.6 } ], "rank": 32, "url": "https://clinicalbenchmarks.ai/models/gemini-3-flash" }, { "model": "claude-opus-4.7", "name": "Claude Opus 4.7", "lab": "anthropic", "score": 64.1, "raw": 64.1, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 504, "valueLabel": "0.519", "normalized": 47.9 }, { "benchmark": "medscribe", "result": 2184, "valueLabel": "82.95", "normalized": 90.3 }, { "benchmark": "medcode", "result": 346, "valueLabel": "54.86", "normalized": 80.1 }, { "benchmark": "physicianbench", "result": 169, "valueLabel": "29.3", "normalized": 38 } ], "rank": 33, "url": "https://clinicalbenchmarks.ai/models/claude-opus-4.7" }, { "model": "gemini-3.8-flash", "name": "Gemini 3.8 Flash", "lab": "google", "score": 64, "raw": 78.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2170, "valueLabel": "84.50", "normalized": 92 }, { "benchmark": "medcode", "result": 1982, "valueLabel": "48.13", "normalized": 64.8 } ], "rank": 34, "url": "https://clinicalbenchmarks.ai/models/gemini-3.8-flash" }, { "model": "minimax-m3", "name": "MiniMax M3", "lab": "minimax", "score": 63.6, "raw": 77.9, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 360, "valueLabel": "87.25", "normalized": 95.2 }, { "benchmark": "medcode", "result": 1988, "valueLabel": "46.29", "normalized": 60.6 } ], "rank": 35, "url": "https://clinicalbenchmarks.ai/models/minimax-m3" }, { "model": "grok-4.6", "name": "Grok 4.6", "lab": "xai", "score": 63.2, "raw": 63.2, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 1805, "valueLabel": "0.485", "normalized": 38.2 }, { "benchmark": "medscribe", "result": 363, "valueLabel": "86.53", "normalized": 94.4 }, { "benchmark": "medcode", "result": 1991, "valueLabel": "44.71", "normalized": 57 } ], "rank": 36, "url": "https://clinicalbenchmarks.ai/models/grok-4.6" }, { "model": "mimo-v2.6-pro", "name": "MiMo V2.6 Pro", "lab": "xiaomi", "score": 62.8, "raw": 77, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2156, "valueLabel": "88.31", "normalized": 96.4 }, { "benchmark": "medcode", "result": 1990, "valueLabel": "44.97", "normalized": 57.6 } ], "rank": 37, "url": "https://clinicalbenchmarks.ai/models/mimo-v2.6-pro" }, { "model": "claude-opus-4.6", "name": "Claude Opus 4.6", "lab": "anthropic", "score": 62.3, "raw": 62.3, "confidence": 1, "boards": 5, "of": 10, "components": [ { "benchmark": "medscribe", "result": 362, "valueLabel": "86.74", "normalized": 94.6 }, { "benchmark": "medcode", "result": 1977, "valueLabel": "49.13", "normalized": 67.1 }, { "benchmark": "medxpertqa-mm", "result": 162, "valueLabel": "64.8", "normalized": 71.2 }, { "benchmark": "medhelm", "result": 121, "valueLabel": "0.456", "normalized": 36.8 }, { "benchmark": "physicianbench", "result": 168, "valueLabel": "31.7", "normalized": 41.8 } ], "rank": 38, "url": "https://clinicalbenchmarks.ai/models/claude-opus-4.6" }, { "model": "gpt-5.1", "name": "GPT-5.1", "lab": "openai", "score": 61.5, "raw": 61.5, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 486, "valueLabel": "0.396", "normalized": 13 }, { "benchmark": "medscribe", "result": 358, "valueLabel": "88.09", "normalized": 96.2 }, { "benchmark": "medcode", "result": 353, "valueLabel": "52.73", "normalized": 75.3 } ], "rank": 39, "url": "https://clinicalbenchmarks.ai/models/gpt-5.1" }, { "model": "claude-sonnet-5", "name": "Claude Sonnet 5", "lab": "anthropic", "score": 61.2, "raw": 61.2, "confidence": 1, "boards": 5, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 207, "valueLabel": "0.578", "normalized": 64.6 }, { "benchmark": "medscribe", "result": 2212, "valueLabel": "76.05", "normalized": 82.4 }, { "benchmark": "medcode", "result": 1984, "valueLabel": "47.54", "normalized": 63.4 }, { "benchmark": "mast", "result": 112, "valueLabel": "56.6", "normalized": 44.6 }, { "benchmark": "physicianbench", "result": 1836, "valueLabel": "37.4", "normalized": 50.9 } ], "rank": 40, "url": "https://clinicalbenchmarks.ai/models/claude-sonnet-5" }, { "model": "glm-5.3", "name": "GLM 5.3", "lab": "zhipu", "score": 61.1, "raw": 74.9, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2155, "valueLabel": "88.81", "normalized": 97 }, { "benchmark": "medcode", "result": 2000, "valueLabel": "42.86", "normalized": 52.8 } ], "rank": 41, "url": "https://clinicalbenchmarks.ai/models/glm-5.3" }, { "model": "grok-4.5", "name": "Grok 4.5", "lab": "xai", "score": 60.6, "raw": 74.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2157, "valueLabel": "86.88", "normalized": 94.8 }, { "benchmark": "medcode", "result": 1997, "valueLabel": "43.29", "normalized": 53.8 } ], "rank": 42, "url": "https://clinicalbenchmarks.ai/models/grok-4.5" }, { "model": "claude-sonnet-4.5", "name": "Claude Sonnet 4.5", "lab": "anthropic", "score": 60.3, "raw": 73.9, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2169, "valueLabel": "84.52", "normalized": 92.1 }, { "benchmark": "medcode", "result": 1993, "valueLabel": "44.13", "normalized": 55.7 } ], "rank": 43, "url": "https://clinicalbenchmarks.ai/models/claude-sonnet-4.5" }, { "model": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "lab": "deepseek", "score": 60, "raw": 60, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2193, "valueLabel": "80.17", "normalized": 87.1 }, { "benchmark": "medcode", "result": 2001, "valueLabel": "42.47", "normalized": 51.9 }, { "benchmark": "medpic-bench", "result": 1546, "valueLabel": "71.7", "normalized": 79.9 }, { "benchmark": "physicianbench", "result": 1839, "valueLabel": "18.7", "normalized": 21.2 } ], "rank": 44, "url": "https://clinicalbenchmarks.ai/models/deepseek-v4-pro" }, { "model": "o3", "name": "o3", "lab": "openai", "score": 59.6, "raw": 73, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2208, "valueLabel": "76.65", "normalized": 83 }, { "benchmark": "medcode", "result": 1985, "valueLabel": "47.29", "normalized": 62.9 } ], "rank": 45, "url": "https://clinicalbenchmarks.ai/models/o3" }, { "model": "hy4-preview", "name": "Hy4 Preview", "lab": "tencent", "score": 59.1, "raw": 72.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2180, "valueLabel": "83.60", "normalized": 91 }, { "benchmark": "medcode", "result": 1998, "valueLabel": "43.25", "normalized": 53.7 } ], "rank": 46, "url": "https://clinicalbenchmarks.ai/models/hy4-preview" }, { "model": "claude-opus-4.1", "name": "Claude Opus 4.1", "lab": "anthropic", "score": 58.2, "raw": 71.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2217, "valueLabel": "73.90", "normalized": 79.9 }, { "benchmark": "medcode", "result": 1986, "valueLabel": "47.23", "normalized": 62.7 } ], "rank": 47, "url": "https://clinicalbenchmarks.ai/models/claude-opus-4.1" }, { "model": "deepseek-v4.1-flash", "name": "DeepSeek V4.1 Flash", "lab": "deepseek", "score": 58, "raw": 71.1, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2162, "valueLabel": "85.50", "normalized": 93.2 }, { "benchmark": "medcode", "result": 2008, "valueLabel": "41.17", "normalized": 48.9 } ], "rank": 48, "url": "https://clinicalbenchmarks.ai/models/deepseek-v4.1-flash" }, { "model": "inkling", "name": "Inkling", "lab": "thinking-machines", "score": 58, "raw": 71.1, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2163, "valueLabel": "85.41", "normalized": 93.1 }, { "benchmark": "medcode", "result": 2007, "valueLabel": "41.19", "normalized": 49 } ], "rank": 49, "url": "https://clinicalbenchmarks.ai/models/inkling" }, { "model": "mimo-v2.6-flash", "name": "MiMo V2.6 Flash", "lab": "xiaomi", "score": 57.8, "raw": 70.8, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2165, "valueLabel": "85.28", "normalized": 92.9 }, { "benchmark": "medcode", "result": 2009, "valueLabel": "41.06", "normalized": 48.7 } ], "rank": 50, "url": "https://clinicalbenchmarks.ai/models/mimo-v2.6-flash" }, { "model": "gpt-5-mini", "name": "GPT-5 mini", "lab": "openai", "score": 57.4, "raw": 70.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2191, "valueLabel": "80.58", "normalized": 87.6 }, { "benchmark": "medcode", "result": 1999, "valueLabel": "43.05", "normalized": 53.2 } ], "rank": 51, "url": "https://clinicalbenchmarks.ai/models/gpt-5-mini" }, { "model": "glm-5.2", "name": "GLM 5.2", "lab": "zhipu", "score": 56.7, "raw": 69.5, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2181, "valueLabel": "83.53", "normalized": 90.9 }, { "benchmark": "medcode", "result": 2011, "valueLabel": "40.77", "normalized": 48 } ], "rank": 52, "url": "https://clinicalbenchmarks.ai/models/glm-5.2" }, { "model": "glm-5.3-flash", "name": "GLM 5.3 Flash", "lab": "zhipu", "score": 56, "raw": 97.1, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2154, "valueLabel": "88.94", "normalized": 97.1 } ], "rank": 53, "url": "https://clinicalbenchmarks.ai/models/glm-5.3-flash" }, { "model": "inkling-small", "name": "Inkling Small", "lab": "thinking-machines", "score": 54.3, "raw": 66.5, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2173, "valueLabel": "84.11", "normalized": 91.6 }, { "benchmark": "medcode", "result": 2025, "valueLabel": "37.89", "normalized": 41.4 } ], "rank": 54, "url": "https://clinicalbenchmarks.ai/models/inkling-small" }, { "model": "gemini-3.1-flash-lite-preview", "name": "Gemini 3.1 Flash Lite Preview", "lab": "google", "score": 53.9, "raw": 66, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2236, "valueLabel": "63.90", "normalized": 68.4 }, { "benchmark": "medcode", "result": 1983, "valueLabel": "47.60", "normalized": 63.6 } ], "rank": 55, "url": "https://clinicalbenchmarks.ai/models/gemini-3.1-flash-lite-preview" }, { "model": "gpt-5.4-nano", "name": "GPT-5.4 nano", "lab": "openai", "score": 53.9, "raw": 66.1, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2206, "valueLabel": "77.09", "normalized": 83.5 }, { "benchmark": "medcode", "result": 2010, "valueLabel": "41.03", "normalized": 48.6 } ], "rank": 56, "url": "https://clinicalbenchmarks.ai/models/gpt-5.4-nano" }, { "model": "qwen3.6-plus", "name": "Qwen3.6 Plus", "lab": "alibaba", "score": 53.5, "raw": 53.5, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2207, "valueLabel": "76.96", "normalized": 83.4 }, { "benchmark": "medcode", "result": 2027, "valueLabel": "36.89", "normalized": 39.2 }, { "benchmark": "medxpertqa-mm", "result": 549, "valueLabel": "68.7", "normalized": 77.9 }, { "benchmark": "physicianbench", "result": 173, "valueLabel": "13.7", "normalized": 13.3 } ], "rank": 57, "url": "https://clinicalbenchmarks.ai/models/qwen3.6-plus" }, { "model": "gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash Lite", "lab": "google", "score": 53.3, "raw": 65.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2227, "valueLabel": "70.89", "normalized": 76.4 }, { "benchmark": "medcode", "result": 1995, "valueLabel": "43.49", "normalized": 54.2 } ], "rank": 58, "url": "https://clinicalbenchmarks.ai/models/gemini-3.5-flash-lite" }, { "model": "qwen-3.7-max", "name": "Qwen 3.7 Max", "lab": "alibaba", "score": 52.9, "raw": 64.8, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2197, "valueLabel": "79.40", "normalized": 86.2 }, { "benchmark": "medcode", "result": 2020, "valueLabel": "38.75", "normalized": 43.4 } ], "rank": 59, "url": "https://clinicalbenchmarks.ai/models/qwen-3.7-max" }, { "model": "grok-4-fast-reasoning", "name": "Grok 4 Fast (Reasoning)", "lab": "xai", "score": 52.7, "raw": 64.6, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2188, "valueLabel": "81.63", "normalized": 88.8 }, { "benchmark": "medcode", "result": 2026, "valueLabel": "37.38", "normalized": 40.3 } ], "rank": 60, "url": "https://clinicalbenchmarks.ai/models/grok-4-fast-reasoning" }, { "model": "gemini-2.5-flash", "name": "Gemini 2.5 Flash", "lab": "google", "score": 52.1, "raw": 90.3, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2183, "valueLabel": "82.98", "normalized": 90.3 } ], "rank": 61, "url": "https://clinicalbenchmarks.ai/models/gemini-2.5-flash" }, { "model": "grok-4", "name": "Grok 4", "lab": "xai", "score": 51.7, "raw": 63.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2200, "valueLabel": "78.15", "normalized": 84.8 }, { "benchmark": "medcode", "result": 2023, "valueLabel": "38.08", "normalized": 41.9 } ], "rank": 62, "url": "https://clinicalbenchmarks.ai/models/grok-4" }, { "model": "gemini-2.5-pro", "name": "Gemini 2.5 Pro", "lab": "google", "score": 51.3, "raw": 51.3, "confidence": 1, "boards": 6, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2218, "valueLabel": "73.55", "normalized": 79.5 }, { "benchmark": "medcode", "result": 1970, "valueLabel": "50.59", "normalized": 70.4 }, { "benchmark": "medpic-bench", "result": 1525, "valueLabel": "54.4", "normalized": 41.2 }, { "benchmark": "medhelm", "result": 119, "valueLabel": "0.529", "normalized": 60.3 }, { "benchmark": "first-do-noharm", "result": 290, "valueLabel": "61.9", "normalized": 25.5 }, { "benchmark": "ehr-complex", "result": 1851, "valueLabel": "0.310", "normalized": 30.6 } ], "rank": 63, "url": "https://clinicalbenchmarks.ai/models/gemini-2.5-pro" }, { "model": "deepseek-v3.2-exp", "name": "DeepSeek-V3.2-Exp", "lab": "deepseek", "score": 50.7, "raw": 87.8, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1842, "valueLabel": "0.590", "normalized": 87.8 } ], "rank": 64, "url": "https://clinicalbenchmarks.ai/models/deepseek-v3.2-exp" }, { "model": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "lab": "deepseek", "score": 50.4, "raw": 87.3, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2192, "valueLabel": "80.36", "normalized": 87.3 } ], "rank": 65, "url": "https://clinicalbenchmarks.ai/models/deepseek-v4-flash" }, { "model": "claude-haiku-4.5", "name": "Claude Haiku 4.5", "lab": "anthropic", "score": 50, "raw": 61.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2167, "valueLabel": "85.23", "normalized": 92.9 }, { "benchmark": "medcode", "result": 2038, "valueLabel": "32.68", "normalized": 29.6 } ], "rank": 66, "url": "https://clinicalbenchmarks.ai/models/claude-haiku-4.5" }, { "model": "minimax-m2.1", "name": "MiniMax-M2.1", "lab": "minimax", "score": 49.2, "raw": 60.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2190, "valueLabel": "80.78", "normalized": 87.8 }, { "benchmark": "medcode", "result": 2032, "valueLabel": "34.08", "normalized": 32.7 } ], "rank": 67, "url": "https://clinicalbenchmarks.ai/models/minimax-m2.1" }, { "model": "ling-3.0-flash", "name": "Ling 3.0 Flash", "lab": "ant-group", "score": 47.6, "raw": 58.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2189, "valueLabel": "80.90", "normalized": 87.9 }, { "benchmark": "medcode", "result": 2040, "valueLabel": "32.27", "normalized": 28.6 } ], "rank": 68, "url": "https://clinicalbenchmarks.ai/models/ling-3.0-flash" }, { "model": "qwen3.7-plus", "name": "Qwen3.7 Plus", "lab": "alibaba", "score": 47.3, "raw": 81.9, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 160, "valueLabel": "71.0", "normalized": 81.9 } ], "rank": 69, "url": "https://clinicalbenchmarks.ai/models/qwen3.7-plus" }, { "model": "deepseek-v3.1", "name": "DeepSeek-V3.1", "lab": "deepseek", "score": 47.1, "raw": 81.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1843, "valueLabel": "0.560", "normalized": 81.6 } ], "rank": 70, "url": "https://clinicalbenchmarks.ai/models/deepseek-v3.1" }, { "model": "qwen-3.5-plus", "name": "Qwen3.5-Plus", "lab": "alibaba", "score": 47, "raw": 81.4, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1553, "valueLabel": "72.4", "normalized": 81.4 } ], "rank": 71, "url": "https://clinicalbenchmarks.ai/models/qwen-3.5-plus" }, { "model": "mimo-v2.5-pro", "name": "MiMo V2.5 Pro", "lab": "xiaomi", "score": 46.1, "raw": 46.1, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2177, "valueLabel": "83.73", "normalized": 91.2 }, { "benchmark": "medcode", "result": 2039, "valueLabel": "32.48", "normalized": 29.1 }, { "benchmark": "physicianbench", "result": 1840, "valueLabel": "16.7", "normalized": 18.1 } ], "rank": 72, "url": "https://clinicalbenchmarks.ai/models/mimo-v2.5-pro" }, { "model": "claude-sonnet-4", "name": "Claude Sonnet 4", "lab": "anthropic", "score": 46.1, "raw": 56.5, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2222, "valueLabel": "72.41", "normalized": 78.2 }, { "benchmark": "medcode", "result": 2029, "valueLabel": "34.96", "normalized": 34.8 } ], "rank": 73, "url": "https://clinicalbenchmarks.ai/models/claude-sonnet-4" }, { "model": "qwen3-32b-sft", "name": "Qwen3-32B-SFT", "lab": "ant-group", "score": 45.9, "raw": 79.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1844, "valueLabel": "0.550", "normalized": 79.6 } ], "rank": 74, "url": "https://clinicalbenchmarks.ai/models/qwen3-32b-sft" }, { "model": "glm-5.1", "name": "GLM 5.1", "lab": "zhipu", "score": 45.6, "raw": 45.6, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2223, "valueLabel": "72.27", "normalized": 78 }, { "benchmark": "medcode", "result": 2003, "valueLabel": "41.60", "normalized": 49.9 }, { "benchmark": "first-do-noharm", "result": 1821, "valueLabel": "57.9", "normalized": 8.8 } ], "rank": 75, "url": "https://clinicalbenchmarks.ai/models/glm-5.1" }, { "model": "qwen-3.8-27b", "name": "Qwen 3.8 27B", "lab": "alibaba", "score": 45.6, "raw": 55.9, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2176, "valueLabel": "83.85", "normalized": 91.3 }, { "benchmark": "medcode", "result": 2049, "valueLabel": "28.70", "normalized": 20.5 } ], "rank": 76, "url": "https://clinicalbenchmarks.ai/models/qwen-3.8-27b" }, { "model": "qwen-3-vl-plus", "name": "Qwen 3 VL Plus", "lab": "alibaba", "score": 45.2, "raw": 55.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2205, "valueLabel": "77.13", "normalized": 83.6 }, { "benchmark": "medcode", "result": 2043, "valueLabel": "31.65", "normalized": 27.2 } ], "rank": 77, "url": "https://clinicalbenchmarks.ai/models/qwen-3-vl-plus" }, { "model": "grok-4-fast-non-reasoning", "name": "Grok 4 Fast (Non-Reasoning)", "lab": "xai", "score": 45, "raw": 55.1, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2195, "valueLabel": "79.72", "normalized": 86.6 }, { "benchmark": "medcode", "result": 2047, "valueLabel": "30.04", "normalized": 23.5 } ], "rank": 78, "url": "https://clinicalbenchmarks.ai/models/grok-4-fast-non-reasoning" }, { "model": "gpt-oss-120b", "name": "GPT OSS 120B", "lab": "openai", "score": 44.8, "raw": 77.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1518, "valueLabel": "70.7", "normalized": 77.6 } ], "rank": 79, "url": "https://clinicalbenchmarks.ai/models/gpt-oss-120b" }, { "model": "qwen3-235b", "name": "Qwen3-235B-A22B-Instruct-2507", "lab": "alibaba", "score": 43.6, "raw": 75.5, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1845, "valueLabel": "0.530", "normalized": 75.5 } ], "rank": 80, "url": "https://clinicalbenchmarks.ai/models/qwen3-235b" }, { "model": "o4-mini", "name": "o4-mini", "lab": "openai", "score": 43.5, "raw": 53.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2231, "valueLabel": "69.14", "normalized": 74.4 }, { "benchmark": "medcode", "result": 2034, "valueLabel": "33.79", "normalized": 32.1 } ], "rank": 81, "url": "https://clinicalbenchmarks.ai/models/o4-mini" }, { "model": "qwen-3.5-flash", "name": "Qwen 3.5 Flash", "lab": "alibaba", "score": 43.4, "raw": 53.2, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2228, "valueLabel": "70.62", "normalized": 76.1 }, { "benchmark": "medcode", "result": 2036, "valueLabel": "33.00", "normalized": 30.3 } ], "rank": 82, "url": "https://clinicalbenchmarks.ai/models/qwen-3.5-flash" }, { "model": "mimo-v2.5", "name": "MiMo V2.5", "lab": "xiaomi", "score": 43.2, "raw": 52.9, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2224, "valueLabel": "72.15", "normalized": 77.9 }, { "benchmark": "medcode", "result": 2042, "valueLabel": "31.89", "normalized": 27.8 } ], "rank": 83, "url": "https://clinicalbenchmarks.ai/models/mimo-v2.5" }, { "model": "qwen-3.5-27b", "name": "Qwen3.5-27B", "lab": "alibaba", "score": 43.1, "raw": 74.7, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1511, "valueLabel": "69.4", "normalized": 74.7 } ], "rank": 84, "url": "https://clinicalbenchmarks.ai/models/qwen-3.5-27b" }, { "model": "qwen-3-max-thinking", "name": "Qwen 3 Max Thinking", "lab": "alibaba", "score": 42.9, "raw": 52.6, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2221, "valueLabel": "72.71", "normalized": 78.5 }, { "benchmark": "medcode", "result": 2044, "valueLabel": "31.37", "normalized": 26.6 } ], "rank": 85, "url": "https://clinicalbenchmarks.ai/models/qwen-3-max-thinking" }, { "model": "mistral-medium-3.5", "name": "Mistral Medium 3.5", "lab": "mistral", "score": 42.8, "raw": 52.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2233, "valueLabel": "67.73", "normalized": 72.8 }, { "benchmark": "medcode", "result": 2035, "valueLabel": "33.75", "normalized": 32 } ], "rank": 86, "url": "https://clinicalbenchmarks.ai/models/mistral-medium-3.5" }, { "model": "gemini-3-pro-11-25", "name": "Gemini 3 Pro (11/25)", "lab": "google", "score": 42.8, "raw": 74.1, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medcode", "result": 1968, "valueLabel": "52.20", "normalized": 74.1 } ], "rank": 87, "url": "https://clinicalbenchmarks.ai/models/gemini-3-pro-11-25" }, { "model": "grok-4.1-fast-reasoning", "name": "Grok 4.1 Fast (Reasoning)", "lab": "xai", "score": 42.7, "raw": 52.3, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2198, "valueLabel": "78.73", "normalized": 85.4 }, { "benchmark": "medcode", "result": 2051, "valueLabel": "28.08", "normalized": 19.1 } ], "rank": 88, "url": "https://clinicalbenchmarks.ai/models/grok-4.1-fast-reasoning" }, { "model": "grok-4.1-fast-non-reasoning", "name": "Grok 4.1 Fast Non-Reasoning", "lab": "xai", "score": 42.4, "raw": 51.9, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2204, "valueLabel": "77.46", "normalized": 84 }, { "benchmark": "medcode", "result": 2050, "valueLabel": "28.35", "normalized": 19.7 } ], "rank": 89, "url": "https://clinicalbenchmarks.ai/models/grok-4.1-fast-non-reasoning" }, { "model": "grok-4.20", "name": "Grok 4.20", "lab": "xai", "score": 42.3, "raw": 42.3, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2237, "valueLabel": "63.41", "normalized": 67.9 }, { "benchmark": "medcode", "result": 2041, "valueLabel": "32.16", "normalized": 28.4 }, { "benchmark": "medxpertqa-mm", "result": 161, "valueLabel": "65.8", "normalized": 72.9 }, { "benchmark": "physicianbench", "result": 295, "valueLabel": "5.3", "normalized": 0 } ], "rank": 90, "url": "https://clinicalbenchmarks.ai/models/grok-4.20" }, { "model": "glm-4.7", "name": "GLM 4.7", "lab": "zhipu", "score": 42.3, "raw": 51.8, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2232, "valueLabel": "68.63", "normalized": 73.8 }, { "benchmark": "medcode", "result": 2037, "valueLabel": "32.77", "normalized": 29.8 } ], "rank": 91, "url": "https://clinicalbenchmarks.ai/models/glm-4.7" }, { "model": "ling-3.0-flash-fin", "name": "Ling 3.0 Flash Fin", "lab": "ant-group", "score": 42.3, "raw": 51.8, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2214, "valueLabel": "75.59", "normalized": 81.8 }, { "benchmark": "medcode", "result": 2048, "valueLabel": "29.30", "normalized": 21.8 } ], "rank": 92, "url": "https://clinicalbenchmarks.ai/models/ling-3.0-flash-fin" }, { "model": "gpt-5-nano", "name": "GPT-5 nano", "lab": "openai", "score": 42.1, "raw": 51.6, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2219, "valueLabel": "72.86", "normalized": 78.7 }, { "benchmark": "medcode", "result": 2046, "valueLabel": "30.44", "normalized": 24.4 } ], "rank": 93, "url": "https://clinicalbenchmarks.ai/models/gpt-5-nano" }, { "model": "minimax-m2.7", "name": "MiniMax-M2.7", "lab": "minimax", "score": 41.9, "raw": 41.9, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2194, "valueLabel": "79.87", "normalized": 86.7 }, { "benchmark": "medcode", "result": 2030, "valueLabel": "34.44", "normalized": 33.6 }, { "benchmark": "physicianbench", "result": 1841, "valueLabel": "8.7", "normalized": 5.4 } ], "rank": 94, "url": "https://clinicalbenchmarks.ai/models/minimax-m2.7" }, { "model": "qwen-3.5-35b-a3b", "name": "Qwen3.5-35B-A3B", "lab": "alibaba", "score": 41.9, "raw": 72.7, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1504, "valueLabel": "68.5", "normalized": 72.7 } ], "rank": 95, "url": "https://clinicalbenchmarks.ai/models/qwen-3.5-35b-a3b" }, { "model": "kimi-k2.6", "name": "Kimi K2.6", "lab": "moonshot", "score": 40.9, "raw": 40.9, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2201, "valueLabel": "78.15", "normalized": 84.8 }, { "benchmark": "medcode", "result": 2018, "valueLabel": "40.14", "normalized": 46.6 }, { "benchmark": "first-do-noharm", "result": 292, "valueLabel": "59.1", "normalized": 13.8 }, { "benchmark": "physicianbench", "result": 172, "valueLabel": "17.0", "normalized": 18.5 } ], "rank": 96, "url": "https://clinicalbenchmarks.ai/models/kimi-k2.6" }, { "model": "grok-4.3", "name": "Grok 4.3", "lab": "xai", "score": 40.8, "raw": 40.8, "confidence": 1, "boards": 3, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2216, "valueLabel": "74.40", "normalized": 80.5 }, { "benchmark": "medcode", "result": 2024, "valueLabel": "38.07", "normalized": 41.8 }, { "benchmark": "mast", "result": 113, "valueLabel": "53.7", "normalized": 0 } ], "rank": 97, "url": "https://clinicalbenchmarks.ai/models/grok-4.3" }, { "model": "gemini-2.5-flash-lite", "name": "Gemini 2.5 Flash Lite", "lab": "google", "score": 40.4, "raw": 49.5, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2213, "valueLabel": "75.82", "normalized": 82.1 }, { "benchmark": "medcode", "result": 2052, "valueLabel": "27.11", "normalized": 16.9 } ], "rank": 98, "url": "https://clinicalbenchmarks.ai/models/gemini-2.5-flash-lite" }, { "model": "claude-sonnet-4.6", "name": "Claude Sonnet 4.6", "lab": "anthropic", "score": 39.5, "raw": 39.5, "confidence": 1, "boards": 4, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 503, "valueLabel": "0.442", "normalized": 26.1 }, { "benchmark": "medpic-bench", "result": 1532, "valueLabel": "64.2", "normalized": 63.1 }, { "benchmark": "physicianbench", "result": 171, "valueLabel": "23.0", "normalized": 28.1 }, { "benchmark": "ehr-complex", "result": 180, "valueLabel": "0.360", "normalized": 40.8 } ], "rank": 99, "url": "https://clinicalbenchmarks.ai/models/claude-sonnet-4.6" }, { "model": "gpt-5.4-mini", "name": "GPT-5.4 mini", "lab": "openai", "score": 39.1, "raw": 67.7, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medhelm", "result": 117, "valueLabel": "0.552", "normalized": 67.7 } ], "rank": 100, "url": "https://clinicalbenchmarks.ai/models/gpt-5.4-mini" }, { "model": "llama-4-maverick", "name": "Llama 4 Maverick", "lab": "meta", "score": 39, "raw": 47.8, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2241, "valueLabel": "54.22", "normalized": 57.3 }, { "benchmark": "medcode", "result": 2028, "valueLabel": "36.51", "normalized": 38.3 } ], "rank": 101, "url": "https://clinicalbenchmarks.ai/models/llama-4-maverick" }, { "model": "gpt-4.1-mini", "name": "GPT-4.1 mini", "lab": "openai", "score": 38.8, "raw": 67.3, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1846, "valueLabel": "0.490", "normalized": 67.3 } ], "rank": 102, "url": "https://clinicalbenchmarks.ai/models/gpt-4.1-mini" }, { "model": "gemma-4-31b", "name": "Gemma 4 31B", "lab": "google", "score": 37.6, "raw": 65.2, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 1825, "valueLabel": "61.3", "normalized": 65.2 } ], "rank": 103, "url": "https://clinicalbenchmarks.ai/models/gemma-4-31b" }, { "model": "gpt-4.1", "name": "GPT-4.1", "lab": "openai", "score": 36.5, "raw": 63.3, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1847, "valueLabel": "0.470", "normalized": 63.3 } ], "rank": 104, "url": "https://clinicalbenchmarks.ai/models/gpt-4.1" }, { "model": "qwen-3.5-9b", "name": "Qwen3.5-9B", "lab": "alibaba", "score": 35.9, "raw": 62.2, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1497, "valueLabel": "63.8", "normalized": 62.2 } ], "rank": 105, "url": "https://clinicalbenchmarks.ai/models/qwen-3.5-9b" }, { "model": "mercury-2.5", "name": "Mercury 2.5", "lab": "inception", "score": 34.6, "raw": 42.4, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2240, "valueLabel": "55.09", "normalized": 58.3 }, { "benchmark": "medcode", "result": 2045, "valueLabel": "31.33", "normalized": 26.5 } ], "rank": 106, "url": "https://clinicalbenchmarks.ai/models/mercury-2.5" }, { "model": "gemma-4-26b-a4b", "name": "Gemma 4 26B A4B", "lab": "google", "score": 34.4, "raw": 59.7, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 1826, "valueLabel": "58.1", "normalized": 59.7 } ], "rank": 107, "url": "https://clinicalbenchmarks.ai/models/gemma-4-26b-a4b" }, { "model": "qwen3-14b-sft", "name": "Qwen3-14B-SFT", "lab": "ant-group", "score": 34.2, "raw": 59.2, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1848, "valueLabel": "0.450", "normalized": 59.2 } ], "rank": 108, "url": "https://clinicalbenchmarks.ai/models/qwen3-14b-sft" }, { "model": "medgemma-27b-text", "name": "MedGemma 27B Text", "lab": "google", "score": 32.5, "raw": 56.4, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1448, "valueLabel": "61.2", "normalized": 56.4 } ], "rank": 109, "url": "https://clinicalbenchmarks.ai/models/medgemma-27b-text" }, { "model": "laguna-m.1", "name": "Laguna M.1", "lab": "poolside", "score": 32, "raw": 39.2, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2235, "valueLabel": "65.91", "normalized": 70.7 }, { "benchmark": "medcode", "result": 2055, "valueLabel": "23.11", "normalized": 7.7 } ], "rank": 110, "url": "https://clinicalbenchmarks.ai/models/laguna-m.1" }, { "model": "fleming-r1-32b", "name": "Fleming-R1-32B", "lab": "ubiquant", "score": 31.7, "raw": 55, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1441, "valueLabel": "60.6", "normalized": 55 } ], "rank": 111, "url": "https://clinicalbenchmarks.ai/models/fleming-r1-32b" }, { "model": "lingshu-32b", "name": "Lingshu-32B", "lab": "alibaba", "score": 30.4, "raw": 52.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1455, "valueLabel": "59.5", "normalized": 52.6 } ], "rank": 112, "url": "https://clinicalbenchmarks.ai/models/lingshu-32b" }, { "model": "gpt-oss-20b", "name": "GPT OSS 20B", "lab": "openai", "score": 29.8, "raw": 51.7, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1490, "valueLabel": "59.1", "normalized": 51.7 } ], "rank": 113, "url": "https://clinicalbenchmarks.ai/models/gpt-oss-20b" }, { "model": "deepseek-v4-flash-0731", "name": "DeepSeek V4 Flash 0731", "lab": "deepseek", "score": 28.6, "raw": 49.5, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medcode", "result": 2004, "valueLabel": "41.41", "normalized": 49.5 } ], "rank": 114, "url": "https://clinicalbenchmarks.ai/models/deepseek-v4-flash-0731" }, { "model": "laguna-xs.2", "name": "Laguna XS.2", "lab": "poolside", "score": 28.2, "raw": 34.6, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2238, "valueLabel": "61.43", "normalized": 65.6 }, { "benchmark": "medcode", "result": 2056, "valueLabel": "21.25", "normalized": 3.5 } ], "rank": 115, "url": "https://clinicalbenchmarks.ai/models/laguna-xs.2" }, { "model": "gemini-2.5-flash-preview-9-25", "name": "Gemini 2.5 Flash Preview (9/25)", "lab": "google", "score": 27.4, "raw": 47.5, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medcode", "result": 2014, "valueLabel": "40.54", "normalized": 47.5 } ], "rank": 116, "url": "https://clinicalbenchmarks.ai/models/gemini-2.5-flash-preview-9-25" }, { "model": "gemini-2.5-flash-7-17", "name": "Gemini 2.5 Flash (7/17)", "lab": "google", "score": 27.2, "raw": 47.1, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medcode", "result": 2016, "valueLabel": "40.36", "normalized": 47.1 } ], "rank": 117, "url": "https://clinicalbenchmarks.ai/models/gemini-2.5-flash-7-17" }, { "model": "llama-3.1-70b", "name": "Llama 3.1 70B", "lab": "meta", "score": 25.4, "raw": 44.1, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1483, "valueLabel": "55.7", "normalized": 44.1 } ], "rank": 118, "url": "https://clinicalbenchmarks.ai/models/llama-3.1-70b" }, { "model": "llama-4-scout", "name": "Llama 4 Scout", "lab": "meta", "score": 25.1, "raw": 30.7, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2242, "valueLabel": "50.59", "normalized": 53.1 }, { "benchmark": "medcode", "result": 2054, "valueLabel": "23.31", "normalized": 8.2 } ], "rank": 119, "url": "https://clinicalbenchmarks.ai/models/llama-4-scout" }, { "model": "gemma-4-12b", "name": "Gemma 4 12B", "lab": "google", "score": 25, "raw": 43.4, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 163, "valueLabel": "48.7", "normalized": 43.4 } ], "rank": 120, "url": "https://clinicalbenchmarks.ai/models/gemma-4-12b" }, { "model": "nemotron-3-ultra", "name": "Nemotron 3 Ultra", "lab": "nvidia", "score": 24.9, "raw": 43.1, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medcode", "result": 2021, "valueLabel": "38.62", "normalized": 43.1 } ], "rank": 121, "url": "https://clinicalbenchmarks.ai/models/nemotron-3-ultra" }, { "model": "huatuogpt-o1-70b", "name": "HuatuoGPT-o1-70B", "lab": "freedom-intelligence", "score": 24.8, "raw": 43, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1434, "valueLabel": "55.2", "normalized": 43 } ], "rank": 122, "url": "https://clinicalbenchmarks.ai/models/huatuogpt-o1-70b" }, { "model": "command-a-plus", "name": "Command A+", "lab": "cohere", "score": 24.1, "raw": 29.5, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2239, "valueLabel": "55.68", "normalized": 59 }, { "benchmark": "medcode", "result": 2057, "valueLabel": "19.72", "normalized": 0 } ], "rank": 123, "url": "https://clinicalbenchmarks.ai/models/command-a-plus" }, { "model": "qwen3-vl-235b-a22b", "name": "Qwen3-VL-235B-A22B", "lab": "alibaba", "score": 24, "raw": 41.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 1827, "valueLabel": "47.6", "normalized": 41.6 } ], "rank": 124, "url": "https://clinicalbenchmarks.ai/models/qwen3-vl-235b-a22b" }, { "model": "qwen3-32b", "name": "Qwen3-32B", "lab": "alibaba", "score": 23.5, "raw": 40.8, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1849, "valueLabel": "0.360", "normalized": 40.8 } ], "rank": 125, "url": "https://clinicalbenchmarks.ai/models/qwen3-32b" }, { "model": "claude-3.7-sonnet", "name": "Claude 3.7 Sonnet", "lab": "anthropic", "score": 20.1, "raw": 34.8, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medhelm", "result": 122, "valueLabel": "0.450", "normalized": 34.8 } ], "rank": 126, "url": "https://clinicalbenchmarks.ai/models/claude-3.7-sonnet" }, { "model": "fleming-r1-7b", "name": "Fleming-R1-7B", "lab": "ubiquant", "score": 19, "raw": 32.9, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1420, "valueLabel": "50.7", "normalized": 32.9 } ], "rank": 127, "url": "https://clinicalbenchmarks.ai/models/fleming-r1-7b" }, { "model": "gemini-2.5-flash-lite-9-25", "name": "Gemini 2.5 Flash Lite (9/25)", "lab": "google", "score": 19, "raw": 33, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medcode", "result": 2031, "valueLabel": "34.19", "normalized": 33 } ], "rank": 128, "url": "https://clinicalbenchmarks.ai/models/gemini-2.5-flash-lite-9-25" }, { "model": "deepseek-r1", "name": "DeepSeek R1", "lab": "deepseek", "score": 18.8, "raw": 23.1, "confidence": 0.816, "boards": 2, "of": 10, "components": [ { "benchmark": "medhelm", "result": 120, "valueLabel": "0.485", "normalized": 46.1 }, { "benchmark": "first-do-noharm", "result": 293, "valueLabel": "55.8", "normalized": 0 } ], "rank": 129, "url": "https://clinicalbenchmarks.ai/models/deepseek-r1" }, { "model": "gpt-4o", "name": "GPT-4o", "lab": "openai", "score": 17.7, "raw": 30.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1850, "valueLabel": "0.310", "normalized": 30.6 } ], "rank": 130, "url": "https://clinicalbenchmarks.ai/models/gpt-4o" }, { "model": "qwen3-14b", "name": "Qwen3-14B", "lab": "alibaba", "score": 16.5, "raw": 28.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1852, "valueLabel": "0.300", "normalized": 28.6 } ], "rank": 131, "url": "https://clinicalbenchmarks.ai/models/qwen3-14b" }, { "model": "baichuan-m2-32b", "name": "Baichuan-M2-32B", "lab": "baichuan", "score": 15.2, "raw": 26.4, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1427, "valueLabel": "47.8", "normalized": 26.4 } ], "rank": 132, "url": "https://clinicalbenchmarks.ai/models/baichuan-m2-32b" }, { "model": "huatuogpt-o1-8b", "name": "HuatuoGPT-o1-8B", "lab": "freedom-intelligence", "score": 10.7, "raw": 18.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1413, "valueLabel": "44.3", "normalized": 18.6 } ], "rank": 133, "url": "https://clinicalbenchmarks.ai/models/huatuogpt-o1-8b" }, { "model": "lingshu-7b", "name": "Lingshu-7B", "lab": "alibaba", "score": 9.4, "raw": 16.3, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1392, "valueLabel": "43.3", "normalized": 16.3 } ], "rank": 134, "url": "https://clinicalbenchmarks.ai/models/lingshu-7b" }, { "model": "healthgpt-pro-8b", "name": "HealthGPT-Pro-8B", "lab": "zju4healthcare", "score": 8.5, "raw": 14.8, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1378, "valueLabel": "42.6", "normalized": 14.8 } ], "rank": 135, "url": "https://clinicalbenchmarks.ai/models/healthgpt-pro-8b" }, { "model": "hulu-med-7b", "name": "Hulu-Med-7B", "lab": "zju-ai4h", "score": 7.7, "raw": 13.4, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1399, "valueLabel": "42.0", "normalized": 13.4 } ], "rank": 136, "url": "https://clinicalbenchmarks.ai/models/hulu-med-7b" }, { "model": "gemma-3-27b", "name": "Gemma 3 27B", "lab": "google", "score": 5.5, "raw": 9.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1469, "valueLabel": "40.3", "normalized": 9.6 } ], "rank": 137, "url": "https://clinicalbenchmarks.ai/models/gemma-3-27b" }, { "model": "gpt-5.5-instant", "name": "GPT-5.5 Instant", "lab": "openai", "score": 5.5, "raw": 9.6, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 211, "valueLabel": "0.384", "normalized": 9.6 } ], "rank": 138, "url": "https://clinicalbenchmarks.ai/models/gpt-5.5-instant" }, { "model": "gemma-4-e4b", "name": "Gemma 4 E4B", "lab": "google", "score": 5.2, "raw": 9, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 1828, "valueLabel": "28.7", "normalized": 9 } ], "rank": 139, "url": "https://clinicalbenchmarks.ai/models/gemma-4-e4b" }, { "model": "llama-3.1-8b", "name": "Llama 3.1 8B", "lab": "meta", "score": 5.1, "raw": 8.9, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1476, "valueLabel": "40.0", "normalized": 8.9 } ], "rank": 140, "url": "https://clinicalbenchmarks.ai/models/llama-3.1-8b" }, { "model": "gemma-3-12b", "name": "Gemma 3 12B", "lab": "google", "score": 4.7, "raw": 8.1, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1462, "valueLabel": "39.6", "normalized": 8.1 } ], "rank": 141, "url": "https://clinicalbenchmarks.ai/models/gemma-3-12b" }, { "model": "medgemma-4b", "name": "MedGemma 4B", "lab": "google", "score": 4.7, "raw": 8.1, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1385, "valueLabel": "39.6", "normalized": 8.1 } ], "rank": 142, "url": "https://clinicalbenchmarks.ai/models/medgemma-4b" }, { "model": "gemini-2.0-flash", "name": "Gemini 2.0 Flash", "lab": "google", "score": 0, "raw": 0, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medhelm", "result": 123, "valueLabel": "0.342", "normalized": 0 } ], "rank": 143, "url": "https://clinicalbenchmarks.ai/models/gemini-2.0-flash" }, { "model": "gemma-4-e2b", "name": "Gemma 4 E2B", "lab": "google", "score": 0, "raw": 0, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medxpertqa-mm", "result": 1829, "valueLabel": "23.5", "normalized": 0 } ], "rank": 144, "url": "https://clinicalbenchmarks.ai/models/gemma-4-e2b" }, { "model": "healthgpt-pro-4b", "name": "HealthGPT-Pro-4B", "lab": "zju4healthcare", "score": 0, "raw": 0, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medpic-bench", "result": 1406, "valueLabel": "36.0", "normalized": 0 } ], "rank": 145, "url": "https://clinicalbenchmarks.ai/models/healthgpt-pro-4b" }, { "model": "mai-thinking-1", "name": "MAI-Thinking-1", "lab": "microsoft", "score": 0, "raw": 0, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "healthbench-professional", "result": 212, "valueLabel": "0.350", "normalized": 0 } ], "rank": 146, "url": "https://clinicalbenchmarks.ai/models/mai-thinking-1" }, { "model": "nemotron-3.5-lightning", "name": "Nemotron 3.5 Lightning", "lab": "nvidia", "score": 0, "raw": 0, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "medscribe", "result": 2243, "valueLabel": "4.27", "normalized": 0 } ], "rank": 147, "url": "https://clinicalbenchmarks.ai/models/nemotron-3.5-lightning" }, { "model": "qwen3-4b", "name": "Qwen3-4B", "lab": "alibaba", "score": 0, "raw": 0, "confidence": 0.577, "boards": 1, "of": 10, "components": [ { "benchmark": "ehr-complex", "result": 1853, "valueLabel": "0.160", "normalized": 0 } ], "rank": 148, "url": "https://clinicalbenchmarks.ai/models/qwen3-4b" } ], "unranked": 0 } }