Medical Diagnosis on agent-CMB
18.34RoundsMedical-CoT*
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Medical-CoT*Specialized LLM=MediTron-7B2025.12 | 18.34 | 66.23 | |
| CoTBase LLM=Qwen3-8B2025.12 | 18.32 | 43.05 | |
| DDOBase LLM=Llama3.1-8B-Instuct2025.12 | 18.01 | 60.93 | |
| DDOBase LLM=Qwen3-8B2025.12 | 17.38 | 63.58 | |
| Huatuo*Specialized LLM=HuatuoGPT-o12025.12 | 16.56 | 62.25 | |
| MEDDxAgentBase LLM=Llama3.1-8B-Instuct2025.12 | 16.48 | 57.62 | |
| CoTBase LLM=Llama3.1-8B-Instuct2025.12 | 16.33 | 50.33 | |
| MEDDxAgentBase LLM=Qwen3-8B2025.12 | 16.09 | 61.59 | |
| MediQBase LLM=Llama3.1-8B-Instuct2025.12 | 15.01 | 60.93 | |
| MCTS-MVBase LLM=Qwen3-8B2025.12 | 14.77 | 60.26 | |
| MCTS-BTBase LLM=Llama3.1-8B-Instuct2025.12 | 14.21 | 42.38 | |
| MCTS-BTBase LLM=Qwen3-8B2025.12 | 13.78 | 54.97 | |
| MediQBase LLM=Qwen3-8B2025.12 | 13.76 | 65.56 | |
| MCTS-MVBase LLM=Llama3.1-8B-Instuct2025.12 | 12.91 | 56.95 | |
| SFTBase LLM=Qwen3-8B2025.12 | 12.04 | 59.6 | |
| CoD*Specialized LLM=DiagnosisGPT-7B2025.12 | 11.99 | 28.5 | |
| AgentClinicBase LLM=Llama3.1-8B-Instuct2025.12 | 11.23 | 59.6 | |
| UoTBase LLM=Llama3.1-8B-Instuct2025.12 | 10.96 | 58.94 | |
| UoTBase LLM=Qwen3-8B2025.12 | 10.71 | 64.28 | |
| SFT-GTBase LLM=Llama3.1-8B-Instuct2025.12 | 10.26 | 51.66 | |
| AgentClinicBase LLM=Qwen3-8B2025.12 | 10 | 58.28 | |
| SFTBase LLM=Llama3.1-8B-Instuct2025.12 | 9.95 | 52.98 | |
| SFT-GTBase LLM=Qwen3-8B2025.12 | 9.93 | 55.63 | |
| MedKGIBase LLM=Llama3.1-8B-Instuct2025.12 | 9.72 | 60.26 | |
| MedKGIBase LLM=Qwen3-8B2025.12 | 9.13 | 68.21 |