Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 564 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-label Classification | NUS-WIDE | 40 | Jun 12, 2026 | ||
| Extreme Classification | LF-AmazonTitles-131K | 40 | Jun 2, 2026 | ||
| Recognition | ModelNet40-LS (test) | 40 | Feb 26, 2026 | ||
| Traffic flow forecasting | PeMS08 | 40 | Apr 21, 2026 | ||
| Few-shot conditional generation | CelebA-64 (train) | 40 | Feb 26, 2026 | ||
| Stereo Image Super-Resolution | KITTI 2015 | 40 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K linear evaluation 1.0 | 40 | Feb 26, 2026 | ||
| Camouflaged Object Segmentation | CAMO 250 images (test) | 40 | Feb 26, 2026 | ||
| Logical Reasoning | LogiQA (dev) | 40 | Feb 26, 2026 | ||
| Univariate long sequence time-series forecasting | Weather 1-hour granularity (test) | 40 | Feb 26, 2026 | ||
| Univariate long sequence time-series forecasting | ETTm1 15-minute granularity (test) | 40 | Feb 26, 2026 | ||
| Univariate long sequence time-series forecasting | ETTh2 1-hour granularity (test) | 40 | Feb 26, 2026 | ||
| Predicate Detection | Visual Relation Detection (VRD) (All) | 40 | Feb 27, 2026 | ||
| Few-shot Image Classification | Meta-Dataset (test) | 40 | Feb 26, 2026 | ||
| Class Incremental Learning | CIFAR100-B0 (test) | 40 | Feb 26, 2026 | ||
| Poisson Denoising | KODAK | 40 | Feb 26, 2026 | ||
| Referring Image Segmentation | UNC (testA) | 40 | Feb 27, 2026 | ||
| Anomaly Detection | Fashion-MNIST | 40 | Feb 26, 2026 | ||
| Relation Extraction | ChemProt | 40 | Feb 26, 2026 | ||
| End-to-end Open-Domain Question Answering | TriviaQA (test) | 40 | Feb 26, 2026 | ||
| Image Classification | SVHN-LT (test) | 40 | Feb 26, 2026 | ||
| kNN Classification | Fashion-MNIST | 40 | Jun 9, 2026 | ||
| Semantic Segmentation | MS COCO 20i | 40 | Feb 26, 2026 | ||
| Multi-person Pose Estimation | OCHuman (val) | 40 | Feb 26, 2026 | ||
| Action Recognition | Kinetics Gameplay to Kinetics (test) | 40 | Feb 26, 2026 |