| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MME Perception | InternVL3-8B | Perception Score1,748.4 | 99 | 26d ago | |
| MME | InternLM-XComposer2 | Perception Score2,242.7 | 43 | 1mo ago | |
| MME | AGLA | Existence Score195 | 26 | 9d ago | |
| MME P | BLIP3-o | MME-P Score1,682.6 | 25 | 15d ago | |
| MME perception-related tasks | HIME | Existence195 | 24 | 2mo ago | |
| BLINK | Accuracy64.95 | 21 | 27d ago | ||
| VStar | ZwZ-4B | Accuracy92.67 | 18 | 3mo ago | |
| HR-8K | Accuracy85 | 18 | 3mo ago | ||
| MMStar | Accuracy83.6 | 16 | 3mo ago | ||
| MME-P (test) | PivotMerge | MME-P Score1,111.1 | 13 | 1mo ago | |
| BabyVision | Accuracy34.51 | 13 | 3mo ago | ||
| ColorBench | Kimi-K2.5 (1T) | Accuracy86.61 | 13 | 3mo ago | |
| MME-RW-cn | Accuracy72.62 | 13 | 3mo ago | ||
| MME-RW-en | Accuracy74.86 | 13 | 3mo ago | ||
| CV-Bench | Accuracy89.57 | 13 | 3mo ago | ||
| HR-4K | Accuracy87.88 | 13 | 3mo ago | ||
| ZoomBench | Accuracy59.29 | 13 | 3mo ago | ||
| HR-Bench 4K | ZwZ | Accuracy84.4 | 11 | 3mo ago | |
| IE-percept | LLaVA1.5-7B | IE-percept Score1,454.98 | 9 | 2mo ago | |
| MME Perception (test) | ShareGPT4V-7B | Score1,567.4 | 7 | 3mo ago | |
| MMMU (val) | Accuracy82 | 6 | 3mo ago | ||
| AI2D | Interfaze-Beta | Accuracy91.51 | 3 | 3mo ago | |
| ChartQA | Interfaze-Beta | Accuracy90.88 | 1 | 3mo ago |