OpenVLM MMMU - Literature: leaderboard
OpenCompass OpenVLM MMMU validation subcategory score for visual college-level questions in literature.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 284 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Nano | 93.3 | #425 |
| 2 | Gemini 1.5 Flash | 93.3 | #618 |
| 3 | Grok 2 (1212) | 93.3 | #496 |
| 4 | GPT-4o ChatGPT | 93.3 | |
| 5 | Gemini 2.5 Pro | 90 | #152 |
| 6 | GPT-5 | 90 | #98 |
| 7 | GPT-4.1 Mini | 90 | #355 |
| 8 | GPT-4.1 Nano | 90 | #731 |
| 9 | InternVL3-8B | 90 | #620 |
| 10 | Gemini 2.0 Flash | 90 | #342 |
| 11 | Gemini 1.5 Flash (002) | 90 | #583 |
| 12 | InternVL2-8B | 90 | #817 |
| 13 | GPT-4.1 (2025-04-14) | 90 | #250 |
| 14 | InternVL3-14B | 90 | #505 |
| 15 | Qwen 2 VL 72B | 90 | #460 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmmu-literature · How It Works · Data refreshed daily, snapshot 2026-10-20.