| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| GQA | ViCrop | Accuracy64.54 | 93 | 8d ago | |
| BLINK | Qwen3-VL-8B-Inst. | Accuracy85.2 | 76 | 1mo ago | |
| V*Bench | Accuracy95.7 | 58 | 1mo ago | ||
| NLVR2 | BEIT-3 | Accuracy92.6 | 49 | 1mo ago | |
| MMBench | ThinkLite | Accuracy88.7 | 48 | 10d ago | |
| NLVR2 (test) | SimVLM_HUGE | Accuracy85.15 | 46 | 12d ago | |
| MM-Vet | UniDFlow | Score82.7 | 40 | 15d ago | |
| MMVP | GPT-4o | Accuracy86.3 | 32 | 1mo ago | |
| MMMU-Pro | Avg@839.42 | 29 | 3d ago | ||
| BLINK | Human | Jigsaw Accuracy99 | 29 | 3d ago | |
| HR-Bench 4K FSP | RTWI | ACC96.5 | 29 | 1mo ago | |
| Geometric Shapes | RoT | Accuracy95.2 | 28 | 1mo ago | |
| MMStar | Insight-V++ | Accuracy68.2 | 27 | 29d ago | |
| LogicVista | Accuracy52.13 | 26 | 3d ago | ||
| DynaMath | Accuracy66.48 | 26 | 3d ago | ||
| MathVerse | Accuracy61.29 | 26 | 3d ago | ||
| Jigsaw | AdaReasoner 7B | Accuracy88.6 | 25 | 1mo ago | |
| HR-Bench 8K | DeepEyes | Overall Score72.6 | 24 | 1mo ago | |
| HR-Bench 4K | SubagentVL | Overall Score0.77 | 24 | 1mo ago | |
| GQA (test) | RandOpt | Accuracy69 | 24 | 25d ago | |
| HalluBench | SaEI | Accuracy71.85 | 24 | 1mo ago | |
| MMMU (val) | Insight-V++ | Accuracy64.8 | 22 | 29d ago | |
| V* | o3 | Overall Score95.7 | 22 | 8d ago | |
| MathVista mini (test) | Insight-V++ | Accuracy77.6 | 21 | 29d ago | |
| NLVR2 (test-P) | BEiT-3 | Accuracy92.6 | 21 | 1mo ago |