MEGA-Bench Task - PMC VQA Medical Image QA — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 89.5 |
| 2 | Gemini 2.5 Pro | 84.2 |
| 3 | Gemma 3 27B (IT) | 78.9 |
| 4 | InternVL3-38B | 78.9 |
| 5 | Claude 3.5 Sonnet (20240620) | 78.9 |
| 6 | Qwen 2 VL 72B | 73.7 |
| 7 | Claude 3.5 Sonnet (20241022) | 73.7 |
| 8 | InternVL2.5-78B | 73.7 |
| 9 | InternVL3-78B | 68.4 |
| 10 | InternVL3-14B | 68.4 |
| 11 | Aquila-VL-2B | 68.4 |
| 12 | Gemini 1.5 Pro (002) | 63.2 |
| 13 | Pixtral-12B | 63.2 |
| 14 | Llama 4 Scout Base | 63.2 |
| 15 | InternVL2-8B | 57.9 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-pmc-vqa-medical-image-qa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.