Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 892 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Facial Landmark Detection | MAFL (test) | 30 | Feb 26, 2026 | ||
| instanceOf triple classification | M-YAGO39K (test) | 30 | Mar 10, 2026 | ||
| Link Prediction | NS | 30 | Feb 26, 2026 | ||
| 3D Point Cloud Classification | ScanNet (test) | 30 | Feb 27, 2026 | ||
| Variational Inference | Omniglot (test) | 30 | Feb 26, 2026 | ||
| Medical Image Segmentation | MSD Pancreas (test) | 30 | May 22, 2026 | ||
| Edge accuracy | NYU-Depth V2 (test) | 30 | Feb 26, 2026 | ||
| Entity Linking | AIDA B | 30 | Feb 26, 2026 | ||
| Unconditional density estimation | POWER (test) | 30 | Feb 26, 2026 | ||
| slide-level tumor localization | Camelyon 16 (test) | 30 | Feb 26, 2026 | ||
| Monocular Depth Estimation | ScanNet (test) | 30 | Mar 31, 2026 | ||
| Optical Flow Estimation | MPI Sintel final (test) | 30 | Feb 26, 2026 | ||
| Action Recognition | Kinetics (test) | 30 | Mar 20, 2026 | ||
| Semantic segmentation | S3DIS 81 (test) | 30 | Feb 26, 2026 | ||
| Action Classification | ActivityNet (val) | 30 | Feb 26, 2026 | ||
| Fake News Stance Detection | FNC 1 (test) | 30 | Feb 26, 2026 | ||
| Unsupervised Domain Adaptation | USPS -> MNIST (test) | 30 | Feb 26, 2026 | ||
| Age Estimation | Morph_Sub | 30 | Feb 26, 2026 | ||
| Face Identification | IJB-A (test) | 30 | Feb 26, 2026 | ||
| Person Re-identification | CUHK01 (486/485 split) | 30 | Feb 26, 2026 | ||
| Aspect Extraction | Laptop (test) | 30 | Feb 26, 2026 | ||
| Action Recognition | IXMAS | 30 | Feb 26, 2026 | ||
| Sentence Relatedness | STS 2014 | 30 | Feb 26, 2026 | ||
| Machine Translation | WMT newstest 2014 | 30 | Feb 27, 2026 | ||
| Video Classification | Sports-1M (test) | 30 | Feb 26, 2026 |