Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1649 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Online Continual Learning | MNIST 10/1 (test) | 20 | Feb 27, 2026 | ||
| Out-of-Distribution Detection | CIFAR10-LT | 20 | Feb 26, 2026 | ||
| Object Detection | MS COCO 2017 | 20 | Feb 26, 2026 | ||
| Reading Comprehension | SQuAD | 20 | Apr 21, 2026 | ||
| Person Re-identification | Market-1501 M (target) | 20 | Apr 30, 2026 | ||
| Semantic Retrieval | AirDialog v1 (test) | 20 | Feb 26, 2026 | ||
| Scientific Reasoning | SciEval | 20 | Feb 26, 2026 | ||
| Scientific Reasoning | CEval Sci | 20 | Feb 26, 2026 | ||
| Gaze Following | VideoAttentionTarget (test) | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | MA | 20 | Feb 27, 2026 | ||
| Mathematical Reasoning | CP | 20 | Feb 27, 2026 | ||
| Time Series Classification | 10 datasets Avg. | 20 | Feb 26, 2026 | ||
| Link Prediction | ogbl-citation2 1.1 (test) | 20 | Feb 26, 2026 | ||
| Link Prediction | ogbl-ppa 1.1 (test) | 20 | Feb 26, 2026 | ||
| Link Prediction | ogbl-collab 1.1 (test) | 20 | Feb 26, 2026 | ||
| Link Prediction | ogbl-ddi 1.1 (test) | 20 | Feb 26, 2026 | ||
| Image Classification | Entity-30 OOD | 20 | Feb 26, 2026 | ||
| Image Classification | Entity-30 ID | 20 | Feb 26, 2026 | ||
| Anomaly Detection | BM-MN | 20 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym Locomotion v2 | 20 | May 15, 2026 | ||
| Image Classification | CIFAR-10 (test) | 20 | Feb 26, 2026 | ||
| Adversarial Attack | AdvBench (query-specific) | 20 | Feb 26, 2026 | ||
| Medical image fusion | MRI-SPECT | 20 | Mar 26, 2026 | ||
| Image Classification | ImageNet and its cross-domain variants (ImageNetV2, ImageNet-S, ImageNet-A, ImageNet-R) (test) | 20 | Apr 23, 2026 | ||
| Classification | energy | 20 | Feb 26, 2026 |