OpenVLM MMBench V1.1 CN - FP-S: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 93.3 |
| 2 | InternVL3-78B | 93.3 |
| 3 | Qwen 2 VL 72B | 92.8 |
| 4 | InternVL2.5-78B | 92.8 |
| 5 | InternVL3-38B | 92.3 |
| 6 | Grok 2 (1212) | 91.2 |
| 7 | Claude 3.5 Sonnet (20241022) | 87.9 |
| 8 | Gemini 1.5 Pro (002) | 87.9 |
| 9 | GPT-4.1 (2025-04-14) | 87.9 |
| 10 | InternVL3-8B | 86.8 |
| 11 | Gemini 1.5 Flash (002) | 86.8 |
| 12 | Qwen 2 VL 7B | 86.1 |
| 13 | Llama 3.2 90B Vision Instruct | 85.4 |
| 14 | InternVL2-8B | 84.2 |
| 15 | GPT-4o ChatGPT | 84.2 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-cn-fp-s · How It Works · Data refreshed daily, snapshot 2026-09-05.