Medical MM Leaderboard - OMVQA: leaderboard
The OMVQA slice of the Medical Multimodal Leaderboard — medical visual question answering over the OMVQA dataset; accuracy (%).
Metric: Accuracy (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-38B | 79.8 | #405 |
| 2 | InternVL3-8B | 79.1 | #620 |
| 3 | InternVL3-14B | 78.9 | #505 |
| 4 | GPT-4.1 | 75.5 | #248 |
| 5 | Gemini 2.5 Flash | 71 | #245 |
| 6 | MedGemma-4B-IT | 69.8 | #853 |
| 7 | Claude Sonnet 4 | 65.5 | #199 |
| 8 | Qwen 2.5 VL 7B | 63.6 | #643 |
Interactive version: theaggregate.ai/benchmark?slug=medical-mm-leaderboard-omvqa · How It Works · Data refreshed daily, snapshot 2026-10-20.