Medical Instruction Following on MultiChallenge (Pass@1)
66.8Pass@1Gemini 3.0 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3.0 ProDecoding=Greedy2026.02 | 66.8 | |
| MedXIAOHEMode=Thinking mode, Decoding=Greedy2026.02 | 61.9 | |
| GPT-5.2 ThinkingMode=Thinking mode, Decoding=Greedy2026.02 | 60 | |
| Gemini 2.5 ProDecoding=Greedy2026.02 | 56.6 |