OpenVLM MMMU - Agriculture: leaderboard
OpenCompass OpenVLM MMMU validation subcategory score for visual college-level questions in agriculture.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around August 2027. 284 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 80 | #152 |
| 2 | GPT-5 | 73.3 | #98 |
| 3 | GPT-4.1 (2025-04-14) | 66.7 | #250 |
| 4 | InternVL3-8B | 63.3 | #620 |
| 5 | GPT-4.5 | 63.3 | #274 |
| 6 | Llama 3.2 90B Vision Instruct | 63.3 | #622 |
| 7 | GPT-4o ChatGPT | 63.3 | |
| 8 | GPT-5 Mini (2025-08-07) | 60 | #172 |
| 9 | Gemini 1.5 Flash | 60 | #618 |
| 10 | Gemini 2.0 Flash | 56.7 | #342 |
| 11 | InternVL3-78B | 56.7 | #352 |
| 12 | InternVL2-8B | 56.7 | #817 |
| 13 | InternVL3-14B | 56.7 | #505 |
| 14 | Gemma 3 27B | 56.7 | #607 |
| 15 | Qwen 2 VL 72B | 56.7 | #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-agriculture · How It Works · Data refreshed daily, snapshot 2026-10-20.