| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMBench | AdaTooler-V-7B | Accuracy87.8 | 265 | 23d ago | |
| MMBench Chinese | Accuracy82.6 | 154 | 4mo ago | ||
| MME | Qwen2.5-VL-7B | Score2,307.6 | 123 | 1mo ago | |
| MME | InternVL3.5-38B | MME Score2,489.7 | 80 | 1mo ago | |
| MME | InternVL2.5 | Total Score2,005 | 71 | 1mo ago | |
| MME | MME Score2,369.1 | 26 | 26d ago | ||
| MME | MME Score1,636.5 | 18 | 26d ago | ||
| MME | FADE | Perception Score1,734.6 | 14 | 25d ago | |
| MMBench EN | Qwen2.5-VL-7B | Accuracy83.9 | 13 | 23d ago | |
| MME | Qwen2.5-VL-7B | MME Score2,303.4 | 13 | 23d ago | |
| MME (test) | Qwen2.5-VL-7B | MME Score2,310 | 7 | 1mo ago | |
| MME | SigLIP-SO400M | Perception Score1,632.9 | 7 | 4mo ago | |
| MME | Uni-DPO | MME Perception + Reasoning Score1,905.1 | 4 | 2mo ago | |
| MME | MiniGPT-4 | Existence Score75 | 3 | 3mo ago |