Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1396 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| CATE Estimation | ACIC 2016 (Out-sample) | 22 | Apr 16, 2026 | ||
| Repo-level Compilation | CompileAgentBench | 22 | Feb 26, 2026 | ||
| Tile-level classification | BACH | 22 | Feb 26, 2026 | ||
| Sequential Recommendation | Amazon Video-Games | 22 | May 1, 2026 | ||
| Long-term forecasting | ETTm2 T=96 | 22 | May 15, 2026 | ||
| Long-term forecasting | ETTm1 T=96 | 22 | May 15, 2026 | ||
| End-to-end text spotting | Total-Text curved text (test) | 22 | Feb 26, 2026 | ||
| Image Classification | OxfordPets 4-shot | 22 | Mar 26, 2026 | ||
| Image Classification | EuroSAT 4-shot | 22 | Mar 26, 2026 | ||
| Person Re-identification | AG-ReID C -> A v2 | 22 | May 19, 2026 | ||
| Object Detection | Cityscapes to Foggy Cityscapes severity 0.02 1.0 (val) | 22 | Feb 26, 2026 | ||
| Video Question Answering | IntentQA (test) | 22 | Feb 26, 2026 | ||
| Action Recognition | CDFSAR HMDB, SSV2, Diving, UCF, RareAct | 22 | Feb 26, 2026 | ||
| Video Prediction | Moving MNIST 10000 sequences (val) | 22 | Feb 26, 2026 | ||
| Text-to-Image Generation | MSCOCO zero-shot 30k | 22 | Mar 4, 2026 | ||
| Image Captioning | COCO Caption | 22 | Feb 26, 2026 | ||
| Vision Understanding | CVBench-2D | 22 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | MOS benchmark | 22 | Feb 26, 2026 | ||
| Scene Text Recognition | Union14M (test) | 22 | Mar 17, 2026 | ||
| Downstream Classification | CIFAR-10 modified (test) | 22 | Feb 26, 2026 | ||
| Image Classification | SVHN | 22 | Feb 26, 2026 | ||
| Anomaly Detection | Kvasir | 22 | May 28, 2026 | ||
| Anomaly Detection | Retina OCT | 22 | Mar 31, 2026 | ||
| Video Generative Performance | Video-based Generative Performance Benchmark | 22 | Mar 13, 2026 | ||
| Image Classification | Air | 22 | Feb 26, 2026 |