General Medical AI Multimodal Benchmarking on GMAI-MMBench
66.81Pass@1Gemini 3.0 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 3.0 ProDecoding=Greedy2026.02 | 66.81 | |
| Gemini 2.5 ProDecoding=Greedy2026.02 | 61.67 | |
| GPT-5.2 ThinkingMode=Thinking mode, Decoding=Greedy2026.02 | 60.42 | |
| MedXIAOHEMode=Thinking mode, Decoding=Greedy2026.02 | 55.21 |