Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1677 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image-level Anomaly Detection | MVTec | 20 | Feb 26, 2026 | ||
| Image Generation | CIFAR-100 (train) | 20 | Feb 26, 2026 | ||
| Few-shot Image Generation | Target Domain (test) | 20 | Feb 26, 2026 | ||
| Vessel Segmentation | ROSE-1 DVC | 20 | Feb 26, 2026 | ||
| Node Classification | Coauthor PHY | 20 | Apr 1, 2026 | ||
| Image Classification | ImageNet (val) | 20 | Feb 26, 2026 | ||
| Layout-to-Image Generation | Visual Genome | 20 | Feb 26, 2026 | ||
| Knowledge Probing | LAMA | 20 | Feb 26, 2026 | ||
| Image Classification | MNIST-360 (test) | 20 | Feb 26, 2026 | ||
| Violence Detection | Movies Fight | 20 | Feb 26, 2026 | ||
| Extreme Summarization | SciTLDR 1.0 (test) | 20 | Feb 26, 2026 | ||
| 3D object reconstruction | ShapeNet Cars (test) | 20 | Feb 26, 2026 | ||
| 3D Object Reconstruction | ShapeNet 32^3 resolution (test) | 20 | Feb 26, 2026 | ||
| POS tagging | Ritter11 T-POS (test) | 20 | Feb 26, 2026 | ||
| Salient Object Detection | DUTRGBD | 20 | Feb 26, 2026 | ||
| Cross-domain Person Re-identification | DukeMTMC -> MSMT17 (test) | 20 | Mar 17, 2026 | ||
| Person Re-identification | SYSU-30k (test) | 20 | Feb 26, 2026 | ||
| Bird's Eye View (BEV) Object Detection | KITTI (test) | 20 | Feb 27, 2026 | ||
| Object Detection | VOC Class Split 3 novel classes 2007 (test) | 20 | Feb 26, 2026 | ||
| Object Detection | VOC Class Split 2 novel classes 2007 (test) | 20 | Feb 26, 2026 | ||
| Object Detection | VOC Class Split 1 novel classes 2007 (test) | 20 | Feb 26, 2026 | ||
| Audio Generation | LJ Speech (test) | 20 | Feb 26, 2026 | ||
| Action Quality Assessment | JIGSAWS | 20 | Jun 29, 2026 | ||
| Commonsense Question Answering | CommonsenseQA blind v1.0 (test) | 20 | Feb 26, 2026 | ||
| Dialogue Response Generation | Persona-Chat | 20 | Feb 26, 2026 |