OpenVLM MMMU - Sociology: leaderboard
OpenCompass OpenVLM MMMU validation subcategory score for visual college-level questions in sociology.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around January 2027. 284 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 90 | #98 |
| 2 | Gemini 2.5 Pro | 80 | #152 |
| 3 | GPT-4o ChatGPT | 80 | |
| 4 | InternVL3-38B | 76.7 | #405 |
| 5 | InternVL3-78B | 76.7 | #352 |
| 6 | GPT-4.1 (2025-04-14) | 76.7 | #250 |
| 7 | Gemma 3 27B | 76.7 | #607 |
| 8 | Gemini 2.0 Flash | 73.3 | #342 |
| 9 | GPT-5 Mini (2025-08-07) | 73.3 | #172 |
| 10 | Grok 2 (1212) | 73.3 | #496 |
| 11 | GPT-4.5 | 73.3 | #274 |
| 12 | Qwen 2 VL 7B | 70 | #750 |
| 13 | Qwen 2 VL 72B | 70 | #460 |
| 14 | Gemma 3 12B | 70 | #671 |
| 15 | Claude 3.5 Sonnet (20241022) | 66.7 | #291 |
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-sociology · How It Works · Data refreshed daily, snapshot 2026-10-20.