Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 493 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR-10 Standard data augmentation (test) | 43 | Feb 26, 2026 | ||
| Image Clustering | USPS | 43 | Feb 26, 2026 | ||
| Fitness Prediction | ProteinGym (overall) | 43 | Apr 14, 2026 | ||
| Clustering | FMNIST | 43 | Jun 16, 2026 | ||
| Multi-task Learning | Cityscapes (test) | 43 | Feb 26, 2026 | ||
| Regression | UCI POWER (test) | 43 | Jun 2, 2026 | ||
| Mortality prediction | PhysioNet 2012 (test) | 43 | May 12, 2026 | ||
| Document Classification | 20 Newsgroups (test) | 43 | Feb 26, 2026 | ||
| Link Sign Prediction | Slashdot | 43 | Feb 26, 2026 | ||
| Link Sign Prediction | Bitcoin-OTC | 43 | Feb 26, 2026 | ||
| Depression Detection | DAIC-WOZ (dev) | 43 | Jul 7, 2026 | ||
| Superresolution | CelebA-HQ (test) | 43 | May 8, 2026 | ||
| 3D Anomaly Detection | Anomaly-ShapeNet 1.0 (test) | 43 | Jun 30, 2026 | ||
| Multiple-choice Question Answering | AQuA | 43 | May 19, 2026 | ||
| Natural Language Reasoning | DROP | 43 | May 25, 2026 | ||
| Semantic Segmentation | Pascal VOC Priority protocol, 1/4 labeled ratio | 43 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC Priority protocol, 1/16 labeled ratio | 43 | Feb 26, 2026 | ||
| Medical Image Classification | Covid (test) | 43 | Feb 26, 2026 | ||
| Human Mesh Recovery | MPI-INF-3DHP | 43 | May 26, 2026 | ||
| Reading Comprehension | BoolQ (test) | 43 | May 12, 2026 | ||
| General Capability | MTBench | 43 | Feb 26, 2026 | ||
| Conversational Retrieval | QReCC (test) | 43 | Feb 26, 2026 | ||
| Anomaly Localization | Real-IAD | 43 | Mar 31, 2026 | ||
| MRI Reconstruction | CMRxRecon 2024 (test) | 42 | Jul 7, 2026 | ||
| Open World Object Detection | M-OWODB | 42 | Jul 7, 2026 |