OpenVLM MMBench V1.1 EN - FP-S — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 94.2 |
| 2 | InternVL3-38B | 93.7 |
| 3 | InternVL3-78B | 93.5 |
| 4 | Qwen 2 VL 72B | 92.3 |
| 5 | InternVL2.5-78B | 92.3 |
| 6 | Gemini 1.5 Pro (002) | 91.6 |
| 7 | Grok 2 (1212) | 91.2 |
| 8 | Qwen 2 VL 7B | 89.3 |
| 9 | InternVL3-14B | 88.9 |
| 10 | GPT-4.1 Mini | 88.6 |
| 11 | Gemini 1.5 Flash (002) | 88.6 |
| 12 | InternVL3-8B | 88.2 |
| 13 | Llama 3.2 90B Vision Instruct | 88.2 |
| 14 | Ovis2-8B | 87.9 |
| 15 | GPT-4.1 (2025-04-14) | 87.2 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-en-fp-s · How the rankings work · Data refreshed daily, snapshot 2026-07-22.