Medical Diagnosis on MedQA agent
9.11RoundsMedKGI
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MedKGIBase LLM=Qwen3-8B2025.12 | 9.11 | 69.81 | |
| SFT-GTBase LLM=Qwen3-8B2025.12 | 9.35 | 50.94 | |
| MedKGIBase LLM=Llama3.1-8B-Instruct2025.12 | 10.2 | 53.77 | |
| SFT-GTBase LLM=Llama3.1-8B-Instruct2025.12 | 10.27 | 40.57 | |
| AgentClinicBase LLM=Llama3.1-8B-Instruct2025.12 | 10.37 | 50 | |
| UoTBase LLM=Llama3.1-8B-Instruct2025.12 | 11.01 | 51.89 | |
| SFTBase LLM=Llama3.1-8B-Instruct2025.12 | 11.21 | 49.06 | |
| AgentClinicBase LLM=Qwen3-8B2025.12 | 11.32 | 59.43 | |
| UoTBase LLM=Qwen3-8B2025.12 | 11.47 | 54.71 | |
| SFTBase LLM=Qwen3-8B2025.12 | 11.51 | 51.89 | |
| MCTS-MVBase LLM=Llama3.1-8B-Instruct2025.12 | 12.86 | 52.83 | |
| CoD*Specialized LLM=DiagnosisGPT-7B2025.12 | 13.32 | 56.6 | |
| MediQBase LLM=Qwen3-8B2025.12 | 13.8 | 61.32 | |
| MediQBase LLM=Llama3.1-8B-Instruct2025.12 | 13.85 | 49.06 | |
| MCTS-BTBase LLM=Qwen3-8B2025.12 | 14.2 | 45.28 | |
| MCTS-MVBase LLM=Qwen3-8B2025.12 | 14.63 | 53.77 | |
| MCTS-BTBase LLM=Llama3.1-8B-Instruct2025.12 | 14.98 | 39.62 | |
| MEDDxAgentBase LLM=Llama3.1-8B-Instruct2025.12 | 16.02 | 49.06 | |
| MEDDxAgentBase LLM=Qwen3-8B2025.12 | 16.44 | 60.38 | |
| Huatuo*Specialized LLM=HuatuoGPT-o12025.12 | 16.7 | 56.6 | |
| DDOBase LLM=Qwen3-8B2025.12 | 17.27 | 61.32 | |
| CoTBase LLM=Llama3.1-8B-Instruct2025.12 | 17.46 | 34.9 | |
| DDOBase LLM=Llama3.1-8B-Instruct2025.12 | 18.39 | 50.94 | |
| CoTBase LLM=Qwen3-8B2025.12 | 18.92 | 24.52 | |
| Medical-CoT*Specialized LLM=MediTron-7B2025.12 | 18.94 | 60.37 |