List your company

Medical Diagnosis on Dynamic Multi-turn Diagnostic Evaluation Chinese

55.31Strict DAPACT
13.065224.03263545.9674Jun 8, 2026

Evaluation results

MethodLinks
PACTSize=8B2026.0655.3185.7976.1661.3357.574.274.0293.39
GPT-4.1Size=–2026.0636.778.8264.8617.2620.419.763.8594.04
Doctor-R1Size=8B2026.0633.572.0957.82122.5723.924.8877
GPT-5Size=–2026.0633.4564.154.0612.8314.4513.925.6479.02
HuatuoGPT-o1-8BSize=8B2026.0630.5470.6157.263.211.543.361.7263.88
Doubao-Seed-1.6Size=–2026.0630.0871.6957.7525.7129.5327.453.9689.6
DeepSeek-R1Size=–2026.0629.3972.256.8519.2620.2122.453.3287
Gemini-3.1 ProSize=–2026.062963.9352.639.2211.038.746.6183.5
HuatuoGPT2-7BSize=7B2026.0627.8563.6451.249.9911.7110.471.854.39
UltraMedicalSize=8B2026.0621.7777.7158.6725.727.5628.073.7371.27
DoctorAgent-RLSize=8B2026.0620.3661.4348.748.252.017.534.3665.65
Reflect-PubMedSize=8B2026.0614.6951.239.410.392.5710.732.7167.7