OpenVLM MMBench V1.1 EN - Image Quality: leaderboard
OpenCompass OpenVLM MMBench V1.1 English split accuracy for image quality assessment.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around January 2027. 284 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Mini (2025-08-07) | 80.6 | #172 |
| 2 | GPT-5 | 74.2 | #98 |
| 3 | Gemini 2.5 Pro | 71.8 | #152 |
| 4 | GPT-4.1 Mini | 68.5 | #355 |
| 5 | GPT-4o ChatGPT | 68.5 | |
| 6 | GPT-4.1 (2025-04-14) | 66.9 | #250 |
| 7 | Qwen 2 VL 72B | 63.7 | #460 |
| 8 | InternVL2.5-78B | 63.7 | #431 |
| 9 | InternVL3-78B | 61.3 | #352 |
| 10 | Claude 3.5 Sonnet | 61.3 | #350 |
| 11 | GPT-4.5 | 61.3 | #274 |
| 12 | GPT-5 Nano | 60.5 | #425 |
| 13 | InternVL3-38B | 60.5 | #405 |
| 14 | Qwen 2.5 VL 7B | 60.5 | #643 |
| 15 | Claude 3.5 Sonnet (20241022) | 59.7 | #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-mmbench-v1-1-en-image-quality · How It Works · Data refreshed daily, snapshot 2026-10-20.