OpenVLM MMBench V1.1 EN - Image Scene: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL2.5-78B | 92.4 |
| 2 | GPT-5 | 91.7 |
| 3 | InternVL2-8B | 91.7 |
| 4 | InternVL3-78B | 91 |
| 5 | GPT-4o ChatGPT | 90.3 |
| 6 | GPT-5 Mini (2025-08-07) | 90.3 |
| 7 | InternVL3-38B | 89.6 |
| 8 | Grok 2 (1212) | 89.6 |
| 9 | InternVL3-8B | 88.9 |
| 10 | InternVL2.5-2B | 88.9 |
| 11 | Claude 3.7 Sonnet | 88.9 |
| 12 | GPT-4.1 (2025-04-14) | 88.9 |
| 13 | Qwen 2 VL 7B | 88.2 |
| 14 | GPT-4.5 | 88.2 |
| 15 | Qwen 2 VL 72B | 87.5 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-en-image-scene · How It Works · Data refreshed daily, snapshot 2026-09-05.