OpenVLM MMBench V1.1 CN - Identity Reasoning — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Flash (002) | 100 |
| 2 | Gemma 3 27B | 100 |
| 3 | InternVL3-78B | 98.7 |
| 4 | InternVL3-8B | 98.7 |
| 5 | Qwen 2 VL 7B | 98.7 |
| 6 | InternVL3-38B | 98.7 |
| 7 | InternVL2.5-78B | 98.7 |
| 8 | Grok 2 (1212) | 98.7 |
| 9 | GPT-4.1 (2025-04-14) | 98.7 |
| 10 | GPT-4o ChatGPT | 98.7 |
| 11 | GPT-5 (2025-08-07) | 98.7 |
| 12 | InternVL2-8B | 97.4 |
| 13 | Qwen 2 VL 72B | 97.4 |
| 14 | Qwen 2 VL 2B | 97.4 |
| 15 | MiniCPM-V-2.6 | 97.4 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-cn-identity-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.