Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 888 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multivariate Time-series Forecasting | ETTm2 15-minute (test) | 30 | Feb 26, 2026 | ||
| Multivariate Time-series Forecasting | ETTm1 15-minute (test) | 30 | Feb 26, 2026 | ||
| Text Classification | R52 (test) | 30 | Feb 26, 2026 | ||
| Pose Estimation | COCO | 30 | Mar 17, 2026 | ||
| Super-Resolution | SCI1K compression (test) | 30 | Feb 26, 2026 | ||
| Super-Resolution | SCI1K (test) | 30 | Jun 9, 2026 | ||
| Place Recognition | University Sectors (U.S.) | 30 | Feb 26, 2026 | ||
| Object Detection | VOC 07+12 | 30 | Feb 26, 2026 | ||
| Continual Learning | CTrL S- stream | 30 | Feb 26, 2026 | ||
| Incremental Semantic Segmentation | Pascal VOC disjoint setup 2012 (VOC 10-1) | 30 | Feb 26, 2026 | ||
| Reinforcement Learning | CartPole Pure | 30 | Feb 26, 2026 | ||
| Reinforcement Learning | MountainCar (Pure) | 30 | Feb 26, 2026 | ||
| Lossless Compression | CIFAR10 (test) | 30 | Feb 26, 2026 | ||
| Robustness | ImageNet-C | 30 | May 21, 2026 | ||
| CS-MRI Reconstruction | CS-MRI (test) | 30 | Feb 26, 2026 | ||
| Node Classification | twitch-gamers (test) | 30 | Feb 26, 2026 | ||
| VAE Log-Likelihood Estimation | Fashion MNIST (test) | 30 | Feb 26, 2026 | ||
| Generative Modeling | Omniglot (train) | 30 | Feb 26, 2026 | ||
| Generative Modeling | Fashion MNIST (train) | 30 | Mar 31, 2026 | ||
| Generative Modeling | Dynamic MNIST (train) | 30 | Feb 26, 2026 | ||
| Age Estimation | UTKFace | 30 | Apr 21, 2026 | ||
| Anomaly Detection | cardio | 30 | Feb 26, 2026 | ||
| Co-saliency Object Detection | CoSOD3k | 30 | Feb 26, 2026 | ||
| Camera Pose Estimation | KITTI sequences 00-02 | 30 | Feb 26, 2026 | ||
| Link Prediction | fb-page | 30 | Feb 26, 2026 |