Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1761 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Named Entity Recognition | Science | 19 | Apr 20, 2026 | ||
| Named Entity Recognition | Politics | 19 | Apr 20, 2026 | ||
| Named Entity Recognition | Literature | 19 | Apr 20, 2026 | ||
| Named Entity Recognition | AI | 19 | Apr 20, 2026 | ||
| Text Classification | Amazon Review 1000 labels (test) | 19 | Feb 26, 2026 | ||
| Text Classification | Amazon Review 250 labels (test) | 19 | Feb 26, 2026 | ||
| Text Classification | Yelp Review (1000 labels) | 19 | Feb 26, 2026 | ||
| Text Classification | Yelp Review 250 labels | 19 | Feb 26, 2026 | ||
| Text Classification | Yahoo! Answer 2000 labels | 19 | Feb 26, 2026 | ||
| Text Classification | Yahoo! Answer 500 labels | 19 | Feb 26, 2026 | ||
| Text Classification | AG News 40 labels | 19 | Feb 26, 2026 | ||
| Mathematical Reasoning | ConceptMath Overall | 19 | Feb 26, 2026 | ||
| Image Matching | MegaDepth-1500 | 19 | May 6, 2026 | ||
| Open-vocabulary semantic segmentation | Pascal Context-459 (test) | 19 | Feb 26, 2026 | ||
| Video Classification | UCF-101 | 19 | Feb 26, 2026 | ||
| Face Verification | IJB-C 1:1 protocol (test) | 19 | Feb 26, 2026 | ||
| Facial Landmark Detection | AFLW Full | 19 | Feb 26, 2026 | ||
| Video Super-Resolution | Vid4 4x (test) | 19 | Feb 26, 2026 | ||
| Pseudo Ground-Truth Generation | PASCAL VOC 2012 (train) | 19 | Feb 26, 2026 | ||
| Graph Classification | Molhiv (scaffold) | 19 | Jun 2, 2026 | ||
| Image Classification | Average 11 datasets (Novel) | 19 | Apr 23, 2026 | ||
| Brain Segmentation | IBIS-subcort one-shot | 19 | Feb 26, 2026 | ||
| Object Detection | OmniLabel | 19 | Mar 30, 2026 | ||
| Point Prediction | OpenImages V7 | 19 | Mar 23, 2026 | ||
| Human Keypoint Detection | MS COCO (test-dev) | 19 | Feb 26, 2026 |