Medical Question Answering on MedXpertQA-Text
69.47Pass@1Gemini 3.0 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3.0 ProDecoding=Greedy2026.02 | 69.47 | |
| MedXIAOHEMode=Thinking mode, Decoding=Greedy2026.02 | 63.14 | |
| GPT-5.2 ThinkingMode=Thinking mode, Decoding=Greedy2026.02 | 55.27 | |
| Gemini 2.5 ProDecoding=Greedy2026.02 | 41.67 |