OpenVLM MMBench V1.1 CN - Image Topic: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 98.9 |
| 2 | InternVL3-78B | 98.9 |
| 3 | InternVL3-8B | 98.9 |
| 4 | Qwen 2 VL 72B | 98.9 |
| 5 | InternVL3-38B | 98.9 |
| 6 | Aquila-VL-2B | 98.9 |
| 7 | GPT-5 Nano | 98.9 |
| 8 | InternVL2.5-78B | 98.9 |
| 9 | Claude 3.5 Sonnet | 98.9 |
| 10 | Gemma 3 4B | 98.9 |
| 11 | Llama 3.2 90B Vision Instruct | 98.9 |
| 12 | GPT-4o ChatGPT | 98.9 |
| 13 | GPT-5 Mini (2025-08-07) | 98.9 |
| 14 | GPT-5 | 97.8 |
| 15 | Claude 3.5 Sonnet (20241022) | 97.8 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-cn-image-topic · How It Works · Data refreshed daily, snapshot 2026-09-05.