Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1680 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Entity Typing | Ultra-Fine Entity Typing (dev) | 20 | Feb 26, 2026 | ||
| Text-to-image synthesis | CUB-200-2011 (test) | 20 | Feb 26, 2026 | ||
| Salient Object Detection | ECSSD 41 (test) | 20 | Feb 26, 2026 | ||
| ImageNet Classification | ImageNet (val) | 20 | Feb 26, 2026 | ||
| Multi-Domain Classification | Office-Home (test) | 20 | Feb 26, 2026 | ||
| Digit Classification | MNIST 10-way 10-shot | 20 | Feb 26, 2026 | ||
| Digit Classification | MNIST 10-way 5-shot | 20 | Feb 26, 2026 | ||
| Digit Classification | MNIST 10-way 1-shot | 20 | Feb 26, 2026 | ||
| Visual Object Tracking | OTB-50 | 20 | Feb 26, 2026 | ||
| Reinforcement Learning | Atari 2600 Qbert | 20 | Apr 6, 2026 | ||
| Gland Segmentation | GlaS Challenge Dataset (test B) | 20 | Feb 26, 2026 | ||
| Gland Segmentation | GlaS Challenge Dataset (test A) | 20 | Feb 26, 2026 | ||
| Instance Segmentation | ScanNet | 20 | Mar 30, 2026 | ||
| Image Categorization | SVHN (0-4) to MNIST (5-9) (test) | 20 | Feb 26, 2026 | ||
| Relation Extraction | NYT10 subset (test) | 20 | Feb 26, 2026 | ||
| Machine Translation | Translation (test) | 20 | Mar 16, 2026 | ||
| Multi-Object Tracking | KITTI Cars (test) | 20 | Feb 26, 2026 | ||
| Video Object Segmentation | FBMS-59 (test) | 20 | Feb 26, 2026 | ||
| Entity recognition | SCIERC (test) | 20 | Feb 26, 2026 | ||
| Image Retrieval | CUB-200 2011 cropped (test) | 20 | Feb 26, 2026 | ||
| Expression Classification | AffectNet (val) | 20 | Feb 26, 2026 | ||
| Action Recognition | NTU RGB+D (Cross-Subject & Cross-View) | 20 | Feb 26, 2026 | ||
| Single-View Reconstruction | ShapeNet | 20 | Feb 26, 2026 | ||
| Text Classification | Yelp Full (test) | 20 | Feb 26, 2026 | ||
| Question Answering | SQuAD-Open (dev) | 20 | Feb 26, 2026 |