OpenVLM MMMU - Diagnostics and Laboratory Medicine — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 (2025-04-14) | 60 |
| 2 | Claude 3.5 Sonnet (20241022) | 56.7 |
| 3 | GPT-5 Mini (2025-08-07) | 56.7 |
| 4 | Gemini 2.5 Pro | 53.3 |
| 5 | InternVL3-8B | 53.3 |
| 6 | Qwen 2 VL 72B | 53.3 |
| 7 | GPT-5 Nano | 53.3 |
| 8 | Claude 3.5 Sonnet | 53.3 |
| 9 | GPT-4o ChatGPT | 53.3 |
| 10 | GPT-5 (2025-08-07) | 53.3 |
| 11 | InternVL3-14B | 50 |
| 12 | Claude 3.7 Sonnet | 50 |
| 13 | InternVL3-78B | 46.7 |
| 14 | Llama 3.2 90B Vision Instruct | 46.7 |
| 15 | GPT-4.5 | 46.7 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmmu-diagnostics-and-laboratory-medicine · How the rankings work · Data refreshed daily, snapshot 2026-07-22.