| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| V* OOD | DeepEyes | Overall Score90 | 20 | 16d ago | |
| HR-Bench-4K OOD | Gemini-2.5-pro | Overall Score87.9 | 20 | 16d ago | |
| MME-RW-Lite ID | TikArt | Overall Score57 | 20 | 16d ago | |
| HR-Bench-8K OOD | DeepEyesV2 | FSP Score88.5 | 19 | 16d ago | |
| V-Star | Overall Accuracy95.7 | 14 | 23d ago | ||
| V* | MAPO | Avg@8 Overall89.5 | 13 | 3mo ago | |
| V-Star, HR-Bench-4K, and HR-Bench-8K | P2R-8B | Average Score85.9 | 12 | 23d ago | |
| HR-Bench 8K | P2R-8B | FSP Score94.5 | 12 | 23d ago | |
| MME Realworld Lite | MAPO | Avg@155.8 | 12 | 3mo ago | |
| MME-RW | Qwen3.5 | Score70.2 | 10 | 1mo ago | |
| HR-8K | Qwen3.5 | Score84.5 | 10 | 1mo ago | |
| HR-4K | Qwen3.5 | Score87.8 | 10 | 1mo ago | |
| VStar | ZwZ | Score91.6 | 10 | 1mo ago | |
| V* | Seed1.5-VL | Accuracy89 | 8 | 4mo ago | |
| MMStar | Qwen3.5 | Score77.5 | 6 | 1mo ago | |
| ZoomBench | V-Zero-4B | Score57.8 | 6 | 1mo ago | |
| V* Benchmark | LLaVA-1.5 + FG-CLIP 2 | AR45.2 | 4 | 2mo ago |