OpenVLM MMBench V1.1 EN - Object Localization: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 94.3 |
| 2 | InternVL3-38B | 91.4 |
| 3 | InternVL3-78B | 90.5 |
| 4 | InternVL2.5-78B | 88.6 |
| 5 | GPT-4.1 (2025-04-14) | 88.6 |
| 6 | GPT-5 Mini (2025-08-07) | 87.6 |
| 7 | Qwen 2 VL 72B | 85.7 |
| 8 | GPT-4o ChatGPT | 85.7 |
| 9 | GPT-5 | 84.8 |
| 10 | Grok 2 (1212) | 83.8 |
| 11 | InternVL3-8B | 81.9 |
| 12 | Claude 3.7 Sonnet | 81.9 |
| 13 | Gemini 1.5 Pro (002) | 81 |
| 14 | Llama 3.2 90B Vision Instruct | 80 |
| 15 | GPT-4.5 | 80 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-en-object-localization · How It Works · Data refreshed daily, snapshot 2026-09-05.