| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MME | Vanilla | MME Score1,862 | 89 | 4d ago | |
| MME (total) | Qwen-VL-Max | MME Total Score2,433.61 | 76 | 1mo ago | |
| MME (test) | Mini-Gemini | Perception Score1,666 | 32 | 1mo ago | |
| MME | LLaVA-1.5 Vanilla 13B | P+C Score1,818 | 13 | 1mo ago | |
| DEMON Benchmark zero-shot evaluation | VPG-C | Multi Modal Dialogue37.5 | 11 | 1mo ago | |
| MME-RW | TTAug | Mean Accuracy31.9 | 10 | 1mo ago | |
| MME | VisionZip | Accuracy1,846 | 7 | 1mo ago | |
| SEED-Bench all | Task Arithmetic | Performance Gain Sum14.54 | 6 | 1mo ago | |
| DataComp | NeuCLIP | Datacomp Average31.89 | 5 | 1mo ago | |
| SEED-Bench-2 Plus | GPTAQ | Score67.85 | 3 | 1mo ago | |
| LVLM-eHub | LLaMA-Adapter | VP Score81 | 3 | 1mo ago |