Medical Question Answering on MedQA USMLE-style
73.02AccuracyMAPLE
Evaluation Results
| Method | Links | |
|---|---|---|
| MAPLESize=8B, Inference Protocol=BoM2026.03 | 73.02 | |
| Med-PRMSize=8B, Inference Protocol=BoM2026.03 | 71.43 | |
| Med-PRMSize=8B, Inference Protocol=SC + RM2026.03 | 69.84 | |
| Llama3.1Size=8B, Inference Protocol=MV2026.03 | 68.25 | |
| UltraMedicalSize=8B, Inference Protocol=MV2026.03 | 68.25 | |
| HuatuoGPT-o1Size=8B, Inference Protocol=pass@12026.03 | 65.89 | |
| HuatuoGPT-o1Size=8B, Inference Protocol=MV2026.03 | 65.11 | |
| Llama3.1Size=8B, Inference Protocol=pass@12026.03 | 62.79 | |
| R1-Distill-LlamaSize=8B, Inference Protocol=MV2026.03 | 61.9 | |
| UltraMedicalSize=8B, Inference Protocol=pass@12026.03 | 57.53 | |
| Gemma 2Size=9B, Inference Protocol=MV2026.03 | 54.76 | |
| Gemma 2Size=9B, Inference Protocol=pass@12026.03 | 52.9 | |
| R1-Distill-LlamaSize=8B, Inference Protocol=pass@12026.03 | 47.1 | |
| R1-Distill-QwenSize=7B, Inference Protocol=MV2026.03 | 34.13 | |
| R1-Distill-QwenSize=7B, Inference Protocol=pass@12026.03 | 18.2 |