OpenVLM MMMU - Geography: leaderboard
OpenCompass OpenVLM MMMU validation subcategory score for visual college-level questions in geography.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around February 2027. 284 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 (2025-04-14) | 76.7 | #250 |
| 2 | Gemini 1.5 Pro (002) | 73.3 | #349 |
| 3 | GPT-4.5 | 73.3 | #274 |
| 4 | Gemini 2.5 Pro | 70 | #152 |
| 5 | GPT-5 Mini (2025-08-07) | 70 | #172 |
| 6 | Grok 2 (1212) | 70 | #496 |
| 7 | GPT-5 | 66.7 | #98 |
| 8 | InternVL3-78B | 66.7 | #352 |
| 9 | Qwen 2 VL 72B | 66.7 | #460 |
| 10 | Gemini 1.5 Flash (002) | 63.3 | #583 |
| 11 | Gemini 1.5 Flash | 63.3 | #618 |
| 12 | Gemini 1.0 Pro | 63.3 | #933 |
| 13 | GPT-4.1 Nano | 60 | #731 |
| 14 | Gemma 3 27B | 60 | #607 |
| 15 | InternVL2.5-78B | 60 | #431 |
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-geography · How It Works · Data refreshed daily, snapshot 2026-10-20.