Medical MM Leaderboard - VQA-RAD — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-38B | 72.7 |
| 2 | Gemini 2.5 Flash | 68.5 |
| 3 | Lingshu-7B | 67.9 |
| 4 | Claude Sonnet 4 | 67.6 |
| 5 | InternVL3-14B | 66.1 |
| 6 | GPT-4.1 | 65 |
| 7 | InternVL3-8B | 61.4 |
Interactive version: aibenchmarks.dev/benchmark?slug=medical-mm-leaderboard-vqa-rad · How the rankings work · Data refreshed daily, snapshot 2026-07-17.