Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 975 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Next-item prediction | Tmall (test) | 28 | Feb 26, 2026 | ||
| Open-set recognition | TinyImageNet 20 closed, 180 open classes 1.0 | 28 | Jul 7, 2026 | ||
| Medical Image Segmentation | BTCV (test) | 28 | May 8, 2026 | ||
| Surgical Phase Recognition | Cholec80 (test) | 28 | May 19, 2026 | ||
| Text-to-Video Generation | MSR-VTT | 28 | Feb 26, 2026 | ||
| Reasoning | BIG-Bench Hard (train) | 28 | Mar 5, 2026 | ||
| Anomaly Detection | CIFAR100-C Gaussian noise (test) | 28 | Feb 26, 2026 | ||
| Text-to-Image | CUHK-PEDES | 28 | Feb 26, 2026 | ||
| Hyperparameter Optimization | JAHS-Bench FM (val) | 28 | Feb 26, 2026 | ||
| Open-World Semi-Supervised Learning | CIFAR-10 (test) | 28 | Feb 26, 2026 | ||
| Classification | Yale | 28 | Feb 26, 2026 | ||
| Target Distribution Fitting | High-dimensional Gaussian | 28 | Feb 26, 2026 | ||
| Image Classification | RSSCN7 | 28 | Jun 23, 2026 | ||
| Video Generation | EvalCrafter | 28 | Apr 8, 2026 | ||
| Super-Resolution | DIV2K-MC (test) | 28 | Feb 26, 2026 | ||
| Visual Question Answering | OK-VQA v1.1 (test) | 28 | Feb 26, 2026 | ||
| Scene Flow Estimation | FlyingThings3D with occlusions (F3Do) (test) | 28 | Feb 26, 2026 | ||
| Class unlearning | CIFAR-10 | 28 | May 12, 2026 | ||
| Resolving Confusion | CIFAR-10 | 28 | Feb 26, 2026 | ||
| Entity Linking | AIDA (testb) | 28 | Feb 27, 2026 | ||
| Audio Classification | ESC50 (test) | 28 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Walker2d Medium | 28 | Jun 4, 2026 | ||
| Classification | SelfRegulationSCP2 | 28 | Feb 26, 2026 | ||
| Classification | SelfRegulationSCP1 | 28 | Feb 26, 2026 | ||
| Math Word Problem Solving | GSM8K official train (dev) | 28 | Feb 26, 2026 |