Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 715 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Face Forgery Detection | FaceForensics++ (test) | 34 | Feb 26, 2026 | ||
| Class-Incremental Learning | CIFAR100 50 steps (test) | 34 | May 20, 2026 | ||
| Few-shot classification | tiered meta-iNat (test) | 34 | Feb 26, 2026 | ||
| Few-shot classification | meta-iNat (test) | 34 | Feb 26, 2026 | ||
| Object Detection | PASCAL VOC | 34 | Jul 9, 2026 | ||
| Image Generation | CelebA-HQ 256x256 (test) | 34 | Feb 26, 2026 | ||
| Text Classification | Yelp.P (test) | 34 | Feb 26, 2026 | ||
| Math Word Problem solving | MathQA (test) | 34 | Feb 26, 2026 | ||
| Sentiment Analysis | Yelp | 34 | May 7, 2026 | ||
| 3D Semantic Segmentation | nuScenes Day to Night (target) | 34 | Feb 26, 2026 | ||
| Novel View Synthesis | ZJU-MoCap | 34 | Apr 29, 2026 | ||
| Image Classification | ImageNet-200 | 34 | May 28, 2026 | ||
| Incremental Semantic Segmentation | Pascal VOC 10-10 Overlap 2012 | 34 | Jun 4, 2026 | ||
| Non-Targeted Adversarial Attack | MNIST | 34 | Feb 26, 2026 | ||
| Few-shot Object Detection | MS-COCO 30-shot (novel classes) | 34 | Feb 26, 2026 | ||
| Few-shot Object Detection | MS-COCO 10-shot (novel classes) | 34 | Feb 26, 2026 | ||
| Trajectory Prediction | UNIV (test) | 34 | May 13, 2026 | ||
| Image Compression | CLIC Professional (val) | 34 | Jun 2, 2026 | ||
| Point cloud completion | MVP (test) | 34 | Feb 26, 2026 | ||
| Stereo Matching | ETH3D (test) | 34 | Apr 14, 2026 | ||
| Domain-incremental learning | CORe50 (test) | 34 | Feb 26, 2026 | ||
| Image Classification | ImageNet-A 1.0 (val) | 34 | Feb 27, 2026 | ||
| Video Anomaly Detection | UCF-Crime (UCFC) (test) | 34 | Feb 26, 2026 | ||
| Image Classification | fMoW (val) | 34 | Mar 4, 2026 | ||
| No-Reference Image Quality Assessment | CLIVE (test) | 34 | Mar 17, 2026 |