OpenVLM MMBench V1.1 EN - Celebrity Recognition — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2 VL 72B | 96.6 |
| 2 | Gemini 2.5 Pro | 94.6 |
| 3 | Qwen 2 VL 7B | 93.2 |
| 4 | Gemini 1.5 Pro (002) | 93.2 |
| 5 | Gemini 1.5 Flash (002) | 91.8 |
| 6 | InternVL3-38B | 91.2 |
| 7 | InternVL3-78B | 90.5 |
| 8 | Gemma 3 27B | 90.5 |
| 9 | Grok 2 (1212) | 89.8 |
| 10 | Llama 3.2 90B Vision Instruct | 89.8 |
| 11 | Gemini 1.0 Pro | 89.8 |
| 12 | Qwen 2 VL 2B | 89.1 |
| 13 | InternVL2.5-78B | 89.1 |
| 14 | Gemini 1.5 Flash | 89.1 |
| 15 | GPT-4.1 Mini | 85.7 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-en-celebrity-recognition · How the rankings work · Data refreshed daily, snapshot 2026-07-22.