Medical Question Answering on MedXpertQA-MM
77.2Pass@1Gemini 3.0 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 3.0 ProDecoding=Greedy2026.02 | 77.2 | |
| GPT-5.2 ThinkingMode=Thinking mode, Decoding=Greedy2026.02 | 73.25 | |
| MedXIAOHEMode=Thinking mode, Decoding=Greedy2026.02 | 71 | |
| Gemini 2.5 ProDecoding=Greedy2026.02 | 45.4 |