OpenVLM MMBench V1.1 CN - Image Emotion — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL2.5-78B | 87.8 |
| 2 | GPT-4.5 | 87.8 |
| 3 | Qwen 2 VL 7B | 86.7 |
| 4 | Ovis2-8B | 86.7 |
| 5 | Gemini 1.5 Flash (002) | 86.7 |
| 6 | GPT-5 Mini (2025-08-07) | 86.7 |
| 7 | InternVL3-8B | 85.6 |
| 8 | GPT-4.1 (2025-04-14) | 85.6 |
| 9 | GPT-5 (2025-08-07) | 85.6 |
| 10 | Gemini 2.5 Pro | 84.4 |
| 11 | GPT-4.1 Mini | 84.4 |
| 12 | Gemini 1.5 Pro (002) | 84.4 |
| 13 | GPT-4o ChatGPT | 84.4 |
| 14 | InternVL3-38B | 83.3 |
| 15 | Gemini 1.5 Pro | 83.3 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-cn-image-emotion · How the rankings work · Data refreshed daily, snapshot 2026-07-22.