Medical Image Classification on US-Derm MCQA
84AccuracyGemini 3 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3 ProTemperature=default2026.04 | 84 | |
| Gemini v2.5 ProScale=Large Models, Task Formulation=zero-shot, multiple choice2025.07 | 81 | |
| Gemini 3 FlashTemperature=default2026.04 | 79.5 | |
| Gemini v2.5 FlashScale=Large Models, Task Formulation=zero-shot, multiple choice2025.07 | 78.4 | |
| MedGemma 1.5Model Scale=4B, Temperature=0.02026.04 | 73.5 | |
| MedGemma 4BScale=Small Models, Task Formulation=zero-shot, multiple choice2025.07 | 71.8 | |
| MedGemma 1Model Scale=4B, Temperature=0.02026.04 | 71.8 | |
| MedGemma 1Model Scale=27B, Temperature=0.02026.04 | 71.7 | |
| Qwen3 VLModel Scale=4B, Temperature=default2026.04 | 68 | |
| Gemma 3 27BScale=Small Models, Task Formulation=zero-shot, multiple choice2025.07 | 66.9 | |
| Gemma 3 4BScale=Small Models, Task Formulation=zero-shot, multiple choice2025.07 | 52.5 |