List your company

Clinical Diagnostic Reasoning Benchmark 1.0 (test)

50.66ICD RecallDr. Assistant
21.0228.71536.4144.105Jan 20, 2026

Evaluation results

MethodLinks
Dr. AssistantNote=Primary proposed model2026.0150.6647.17
Gemini-3-Pro-PreviewAccess=Closed-source2026.0147.4853.33
GPT-5Access=Closed-source2026.0146.5148.42
HuatuoGPT-o1-72BAccess=Open-source, Domain=Medical2026.0144.652.11
Qwen3-32BAccess=Open-source, Domain=Non-medical2026.0143.5646.6
Qwen3-14BAccess=Open-source, Domain=Non-medical2026.0142.9846
Gemini-2.5-FlashAccess=Closed-source2026.0142.8844.97
Grok 4 FastAccess=Closed-source2026.0142.8451.59
DeepSeek-R1-Distill-14BAccess=Open-source, Domain=Non-medical2026.0139.1342.67
Doctor-R1-8BAccess=Open-source, Domain=Medical2026.0138.7348
Baichuan-M2-32BAccess=Open-source, Domain=Medical2026.0136.8745.17
Med42-v2-8BAccess=Open-source, Domain=Medical2026.0127.8730.81
Llama3-OpenBioLLM-70BAccess=Open-source, Domain=Medical2026.0122.1627.55