List your company

Multi-Turn Medical Dialogue on MedicalExam

74.33AccuracyMEDIQ
27.259639.479851.763.9202Feb 10, 2026

Evaluation results

MethodLinks
MEDIQModel=Gemini-2.5-Pro, Method Type=Prompt2026.0274.33
ATPO (U1 + U2)Model=Qwen3-8B, Method Type=SFT+RL2026.0265.87
ATPO (U1)Model=Qwen3-8B, Method Type=SFT+RL2026.0265.52
TreePOModel=Qwen3-8B, Method Type=SFT+RL2026.0265.33
MEDIQModel=GPT-4o, Method Type=Prompt2026.0264
GRPOModel=Qwen3-8B, Method Type=SFT+RL2026.0260.93
ATPO (U1 + U2)Model=Qwen3-4B, Method Type=SFT+RL2026.0259.73
PPO (MDP)Model=Qwen3-8B, Method Type=SFT+RL2026.0259.2
PPO (H-MDP)Model=Qwen3-8B, Method Type=SFT+RL2026.0259.07
ATPO (U1)Model=Qwen3-4B, Method Type=SFT+RL2026.0256.8
TreePOModel=Qwen3-4B, Method Type=SFT+RL2026.0256.13
SFTModel=Qwen3-8B, Method Type=SFT2026.0255.87
GRPOModel=Qwen3-4B, Method Type=SFT+RL2026.0253.87
PPO (H-MDP)Model=Qwen3-4B, Method Type=SFT+RL2026.0252.4
DirectModel=Qwen3-8B, Method Type=Prompt2026.0252.4
MEDIQModel=Qwen3-8B, Method Type=Prompt2026.0251.87
DFTModel=Qwen3-8B, Method Type=SFT2026.0251.86
PPO (MDP)Model=Qwen3-4B, Method Type=SFT+RL2026.0250.13
SFTModel=Qwen3-4B, Method Type=SFT2026.0248.93
DirectModel=Qwen3-4B, Method Type=Prompt2026.0248.13
MEDIQModel=Qwen3-4B, Method Type=Prompt2026.0245.87
ATPO (U1)Model=Qwen3-1.7B, Method Type=SFT+RL2026.0245.73
TreePOModel=Qwen3-1.7B, Method Type=SFT+RL2026.0243.33
ATPO (U1 + U2)Model=Qwen3-1.7B, Method Type=SFT+RL2026.0243.2
DFTModel=Qwen3-4B, Method Type=SFT2026.0243.07
GRPOModel=Qwen3-1.7B, Method Type=SFT+RL2026.0242.93
PPO (MDP)Model=Qwen3-1.7B, Method Type=SFT+RL2026.0239.33
PPO (H-MDP)Model=Qwen3-1.7B, Method Type=SFT+RL2026.0239.33
DirectModel=Qwen3-1.7B, Method Type=Prompt2026.0235.07
MEDIQModel=Qwen3-1.7B, Method Type=Prompt2026.0234
SFTModel=Qwen3-1.7B, Method Type=SFT2026.0232.27
DFTModel=Qwen3-1.7B, Method Type=SFT2026.0229.07