Medical Diagnosis on DiagnosisArena
45.57Pass@1GPT-5.2 Thinking
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.2 ThinkingMode=Thinking mode, Decoding=Greedy2026.02 | 45.57 | |
| MedXIAOHEMode=Thinking mode, Decoding=Greedy2026.02 | 42.08 | |
| Gemini 3.0 ProDecoding=Greedy2026.02 | 26.45 | |
| Gemini 2.5 ProDecoding=Greedy2026.02 | 20.87 |