Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1966 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Calibration | GLD InD-domains v2 | 18 | Feb 26, 2026 | ||
| Calibration | WILDS-RxRx1 (OOD-domains) | 18 | Feb 26, 2026 | ||
| Calibration | WILDS-RxRx1 (InD-domains) | 18 | Feb 26, 2026 | ||
| Image Classification | Small-ImageNet-127 | 18 | Jun 16, 2026 | ||
| Biomedical Knowledge Probing | MedLAMA Full Set 1.0 | 18 | Feb 27, 2026 | ||
| Zero-shot performance prediction | UDPOS | 18 | Feb 26, 2026 | ||
| Zero-shot performance prediction | WikiANN | 18 | Feb 26, 2026 | ||
| Zero-shot performance prediction | XNLI | 18 | Feb 26, 2026 | ||
| Image Classification | ImageNet 2012 (val) | 18 | Feb 26, 2026 | ||
| 3D Shape Retrieval | ModelNet-40 | 18 | Feb 26, 2026 | ||
| Tweet Classification | TweetEval 1.0 (test) | 18 | Feb 26, 2026 | ||
| Out-of-distribution Detection | ISUN | 18 | Feb 26, 2026 | ||
| Multi-Image Super-Resolution | Synthetic 15 images (test) | 18 | Feb 26, 2026 | ||
| Binary Classification | TABFACT (test) | 18 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10-LT Imbalance Ratio 50 (test) | 18 | Feb 26, 2026 | ||
| Behavior Classification | CalMS21 (test) | 18 | Mar 11, 2026 | ||
| Line Segment Detection | Wireframe | 18 | Feb 26, 2026 | ||
| Image Classification | GBCU (test) | 18 | Feb 26, 2026 | ||
| Semantic Segmentation | Cityscapes 1/4 subset (val) | 18 | Feb 26, 2026 | ||
| Saliency Detection | DUT-LF | 18 | Feb 26, 2026 | ||
| Burst Super-resolution | SyntheticBurst (val) | 18 | Feb 26, 2026 | ||
| Offline Task-Incremental Continual Learning | CIFAR-100 Sequential | 18 | Feb 26, 2026 | ||
| Offline Class-Incremental Continual Learning | CIFAR-100 Sequential | 18 | Feb 26, 2026 | ||
| Offline Task-Incremental Continual Learning | Sequential CIFAR-10 | 18 | Feb 26, 2026 | ||
| Offline Class-Incremental Continual Learning | CIFAR-10 Sequential | 18 | Feb 26, 2026 |