List your company

Question Answering on CMB Exam

59.33Accuracy (EM)ProMed(S#1+2)
14.235625.942837.6549.3572Aug 19, 2025

Evaluation results

MethodLinks
ProMed(S#1+2)Backbone=LLaMA3.1-8B, Method Type=SFT+RL2025.0859.33
ProMed(S#1+2)Backbone=Qwen3-1.7B, Method Type=SFT+RL2025.0851.98
ProMed(S#1)Backbone=LLaMA3.1-8B, Method Type=SFT2025.0851.78
ProMed(S#1)+GRPOBackbone=LLaMA3.1-8B, Method Type=SFT+RL2025.0851.43
MCTS-MVBackbone=LLaMA3.1-8B, Method Type=Prompt2025.0850.44
SFT-GTBackbone=LLaMA3.1-8B, Method Type=SFT2025.0849.93
ProMed(S#1)+DPOBackbone=LLaMA3.1-8B, Method Type=SFT+RL2025.0847.87
SFTBackbone=LLaMA3.1-8B, Method Type=SFT2025.0847.15
ProMed(S#1)+GRPOBackbone=Qwen3-1.7B, Method Type=SFT+RL2025.0846.61
ProMed(S#1+2)Backbone=LLaMA3.2-3B, Method Type=SFT+RL2025.0846.25
ProMed(S#1)Backbone=Qwen3-1.7B, Method Type=SFT2025.0845.69
ProMed(S#1)Backbone=LLaMA3.2-3B, Method Type=SFT2025.0845.07
ProMed(S#1)+GRPOBackbone=LLaMA3.2-3B, Method Type=SFT+RL2025.0844.76
CoTBackbone=LLaMA3.1-8B, Method Type=Prompt2025.0844.75
VanillaBackbone=LLaMA3.1-8B, Method Type=Prompt2025.0844.49
SFTBackbone=Qwen3-1.7B, Method Type=SFT2025.0844.3
DirectBackbone=LLaMA3.1-8B, Method Type=Prompt2025.0844.1
UoTBackbone=LLaMA3.1-8B, Method Type=Prompt2025.0844.04
UoTBackbone=Qwen3-1.7B, Method Type=Prompt2025.0843.79
SFT-GTBackbone=Qwen3-1.7B, Method Type=SFT2025.0843.65
SFTBackbone=LLaMA3.2-3B, Method Type=SFT2025.0843.6
DirectBackbone=LLaMA3.2-3B, Method Type=Prompt2025.0843.1
MCTS-BTBackbone=LLaMA3.1-8B, Method Type=Prompt2025.0842.95
ProMed(S#1)+DPOBackbone=LLaMA3.2-3B, Method Type=SFT+RL2025.0842.87
ProMed(S#1)+DPOBackbone=Qwen3-1.7B, Method Type=SFT+RL2025.0842.42
SFT-GTBackbone=LLaMA3.2-3B, Method Type=SFT2025.0842.37
UoTBackbone=LLaMA3.2-3B, Method Type=Prompt2025.0840.57
DialogTBackbone=LLaMA3.1-8B, Method Type=SFT2025.0838.37
MCTS-MVBackbone=Qwen3-1.7B, Method Type=Prompt2025.0837.93
CoTBackbone=LLaMA3.2-3B, Method Type=Prompt2025.0834.79
DialogTBackbone=LLaMA3.2-3B, Method Type=SFT2025.0834.07
VanillaBackbone=LLaMA3.2-3B, Method Type=Prompt2025.0833.45
MEDIQBackbone=LLaMA3.1-8B, Method Type=Prompt2025.0833.16
DialogTBackbone=Qwen3-1.7B, Method Type=SFT2025.0832.43
MEDIQBackbone=Qwen3-1.7B, Method Type=Prompt2025.0831.13
CoTBackbone=Qwen3-1.7B, Method Type=Prompt2025.0831.04
MCTS-BTBackbone=Qwen3-1.7B, Method Type=Prompt2025.0830.28
MCTS-MVBackbone=LLaMA3.2-3B, Method Type=Prompt2025.0830.03
VanillaBackbone=Qwen3-1.7B, Method Type=Prompt2025.0829.01
MCTS-BTBackbone=LLaMA3.2-3B, Method Type=Prompt2025.0821.5
DirectBackbone=Qwen3-1.7B, Method Type=Prompt2025.0819.34
MEDIQBackbone=LLaMA3.2-3B, Method Type=Prompt2025.0815.97