V*
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Reasoning | V* | Accuracy96.03 | 72 | |
| Visual Perception and Reasoning | V* | Overall Accuracy91.1 | 60 | |
| High-resolution perception | V* | Overall Score89.53 | 55 | |
| Visual Search | V* benchmark | Overall Success Rate91.1 | 54 | |
| Visual Search | V* | Accuracy92.67 | 53 | |
| Visual Question Answering | V* | Accuracy74.35 | 45 | |
| Visual Perception | V* | Score89 | 42 | |
| Visual Reasoning | V* | Overall Score95.7 | 30 | |
| Visual Grounding | V* | Accuracy83.77 | 29 | |
| Fine-grained Visual Reasoning | V* OOD | Overall Score90 | 20 | |
| Visual Perception | V* v1.0 (test) | Score84.35 | 20 | |
| Fine-grained image perception | V* | Attribute Score91.3 | 19 | |
| Fine-grained VQA | V* | Accuracy93.2 | 18 | |
| Vision-Intensive Perception | V* Benchmark | Attr Score84.4 | 18 | |
| Multimodal Perception | V* | Accuracy89.6 | 17 | |
| Visual Grounding | V* | Average Accuracy91.1 | 17 | |
| Spatial Reasoning | V* | Accuracy86.9 | 16 | |
| Reasoning | V* | Pass@497.9 | 16 | |
| Perception | V* | Pass@190.2 | 16 | |
| Multimodal Reasoning | V* | Accuracy87 | 16 | |
| Pixel-centric Understanding | V* | Score72.7 | 15 | |
| Semantic Segmentation | V20 | mIoU83.8 | 15 | |
| Visual Reasoning | V* cross-domain (test) | Accuracy79.06 | 15 | |
| Fine-grained visual search | V* | Overall Score91.1 | 14 | |
| Perception | V* | Overall Score95.7 | 13 |
Showing 25 of 63 rows