Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 981 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Generalization Gap Prediction | CIFAR-10 | 28 | Jun 30, 2026 | ||
| Isolated Sign Language Recognition | WLASL 300 | 28 | Feb 26, 2026 | ||
| Skin Lesion Classification | ISIC 3-way 5-shot 2018 (test) | 28 | Feb 26, 2026 | ||
| Skin Lesion Classification | ISIC 3-way 3-shot 2018 (test) | 28 | Feb 26, 2026 | ||
| Skin Lesion Classification | ISIC 3-way 1-shot 2018 (test) | 28 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 OOD (Averaged Performance) (test) | 28 | Feb 27, 2026 | ||
| Face Parsing | CelebAMask-HQ | 28 | Feb 26, 2026 | ||
| Action step localization | CrossTask | 28 | Feb 27, 2026 | ||
| Classification | tic-tac-toe | 28 | May 12, 2026 | ||
| Grayscale JPEG image restoration | BSDS500 (test) | 28 | Feb 26, 2026 | ||
| Grayscale JPEG image restoration | LIVE1 (test) | 28 | Feb 26, 2026 | ||
| Grayscale JPEG image restoration | Classic5 (test) | 28 | Feb 26, 2026 | ||
| Knowledge Base Question Answering | LC-QuAD 1.0 (test) | 28 | Feb 26, 2026 | ||
| Anomaly Detection | Fishyscapes Static | 28 | May 20, 2026 | ||
| Anomaly Detection | Fishyscapes Lost & Found | 28 | May 20, 2026 | ||
| Image Classification | ImageNet-200 (test) | 28 | Feb 26, 2026 | ||
| Machine Translation | BMELD Ch=>En (test) | 28 | Feb 26, 2026 | ||
| Machine Translation | BMELD (En=>Ch) (test) | 28 | Feb 26, 2026 | ||
| Machine Translation | BConTrasT De=>En (test) | 28 | Feb 26, 2026 | ||
| Image Classification | ImageNet16-120 (test) | 28 | Apr 2, 2026 | ||
| Image Classification | ImageNet16-120 (val) | 28 | Apr 2, 2026 | ||
| Named Entity Recognition | Resume (test) | 28 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 Long-Tailed (rho=50) (test) | 28 | May 19, 2026 | ||
| Nested Named Entity Recognition | KBP English 2017 (test) | 28 | Feb 26, 2026 | ||
| Image Classification | Aircraft (test) | 28 | Feb 26, 2026 |