Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 559 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Detection | MVTec AD | 40 | Feb 26, 2026 | ||
| Handwritten Mathematical Expression Recognition | CROHME 2016 | 40 | Feb 26, 2026 | ||
| Medical Image Classification | ISIC 2018 | 40 | May 27, 2026 | ||
| 2D Classification | NIH ChestX-ray (test) | 40 | Feb 26, 2026 | ||
| Shadow Removal | ISTD | 40 | Apr 21, 2026 | ||
| Procedure Planning | COIN T=3 (test) | 40 | Mar 11, 2026 | ||
| Causal Discovery | Synthetic DAG data (test) | 40 | Feb 26, 2026 | ||
| Causal Discovery | Synthetic DAG data | 40 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | Flickr | 40 | Apr 15, 2026 | ||
| Controlled Generation | Sentiment Control | 40 | May 19, 2026 | ||
| Controlled Generation | Topic Control | 40 | May 19, 2026 | ||
| Class-Incremental Learning | CIFAR-100 10T | 40 | May 13, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP n=125 (generalization) | 40 | Jun 11, 2026 | ||
| Image Segmentation | ISIC 2016 (test) | 40 | Feb 26, 2026 | ||
| General Language Understanding | GLUE v1 (test dev) | 40 | Feb 26, 2026 | ||
| Video Understanding | Perception (test) | 40 | Mar 19, 2026 | ||
| Few-shot Cancer Subtype Classification | Human Lung (NSCLC) 1,946 slides (test) | 40 | Feb 26, 2026 | ||
| Few-shot Cancer Subtype Classification | Human Breast (BRCA) 1,265 slides (test) | 40 | Feb 26, 2026 | ||
| Molecular property prediction | BACE 50-shot (test) | 40 | May 18, 2026 | ||
| Molecular property prediction | HIV 50-shot (test) | 40 | May 18, 2026 | ||
| Molecular property prediction | MUV 50-shot (test) | 40 | May 18, 2026 | ||
| Molecular property prediction | ClinTox 50-shot (test) | 40 | May 18, 2026 | ||
| Molecular property prediction | SIDER 50-shot (test) | 40 | May 18, 2026 | ||
| Molecular property prediction | ToxCast 50-shot (test) | 40 | May 18, 2026 | ||
| Molecular property prediction | Tox21 50-shot (test) | 40 | May 18, 2026 |