MEGA-Bench Task - MMMU Physics Chemistry MCQ — leaderboard
Metric: Task Score (%). Source: huggingface.co. 27 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro (002) | 92.9 |
| 2 | GPT-4o | 85.7 |
| 3 | Claude 3.5 Sonnet (20241022) | 71.4 |
| 4 | Qwen 2 VL 72B | 64.3 |
| 5 | GPT-4o Mini | 64.3 |
| 6 | Claude 3.5 Sonnet (20240620) | 64.3 |
| 7 | Gemini 1.5 Flash (002) | 57.1 |
| 8 | InternVL2.5-78B | 57.1 |
| 9 | Qwen 2 VL 7B | 28.6 |
| 10 | Pixtral-12B | 28.6 |
| 11 | InternVL2.5-2B | 28.6 |
| 12 | InternVL2-8B | 21.4 |
| 13 | Aquila-VL-2B | 21.4 |
| 14 | Qwen 2 VL 2B | 7.1 |
| 15 | MiniCPM-V-2.6 | 0 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-mmmu-physics-chemistry-mcq · How the rankings work · Data refreshed daily, snapshot 2026-07-22.