| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Interactive Medical Diagnosis | DiagnosisArena | ICR73.8 | 12 | |
| Medical Diagnosis | DiagnosisArena (test) | Match (LLM-as-a-Judge)31.88 | 9 | |
| Diagnosis | DiagnosisArena | Top-1 Accuracy36.36 | 7 | |
| Medical Knowledge Evaluation | DiagnosisArena | Accuracy61.11 | 5 | |
| Medical Diagnosis | DiagnosisArena | Pass@145.57 | 4 |