OpenVLM MMBench V1.1 EN - CP: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 86.9 |
| 2 | GPT-5 Mini (2025-08-07) | 86.3 |
| 3 | GPT-4o ChatGPT | 85.4 |
| 4 | InternVL2.5-78B | 84.1 |
| 5 | GPT-4.1 (2025-04-14) | 84.1 |
| 6 | Gemini 2.5 Pro | 83.7 |
| 7 | GPT-4.1 Mini | 82.6 |
| 8 | GPT-4.5 | 82.6 |
| 9 | InternVL3-38B | 82.2 |
| 10 | Qwen 2 VL 72B | 82 |
| 11 | InternVL3-78B | 81.9 |
| 12 | Qwen 2 VL 7B | 81.3 |
| 13 | InternVL3-8B | 80.9 |
| 14 | Gemini 1.5 Pro (002) | 80.4 |
| 15 | Gemini 1.5 Flash (002) | 79.8 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-en-cp · How It Works · Data refreshed daily, snapshot 2026-09-05.