Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 529 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Scene Flow Estimation | Argoverse 2 (test) | 41 | May 19, 2026 | ||
| Multiple Choice VideoQA | IntentQA | 41 | Feb 26, 2026 | ||
| Video Object Detection | ImageNet VID v1.0 (val) | 41 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC overlapped setting (15-1 (6 steps)) | 41 | Feb 26, 2026 | ||
| Classification | Audiovision-MNIST (test) | 41 | Feb 26, 2026 | ||
| Machine Translation | IT All-domain datastore (test) | 41 | Feb 26, 2026 | ||
| Scene Graph Detection | Action Genome | 41 | Apr 23, 2026 | ||
| Multivariate time series prediction | PEMS04 | 41 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K standard (val test) | 41 | Apr 6, 2026 | ||
| Video Camouflaged Object Detection | CAD (test) | 41 | Apr 14, 2026 | ||
| Novel Expression Synthesis | NeRSemble | 41 | Jun 30, 2026 | ||
| Object Detection | ODinW (test) | 41 | Feb 26, 2026 | ||
| TOS classification | Cifar100 | 41 | May 29, 2026 | ||
| Gait Recognition | SUSTech1K | 41 | May 22, 2026 | ||
| Multivariate Forecasting | PEMS04 (test) | 41 | Feb 26, 2026 | ||
| Class-Incremental Learning | FGVC-aircraft | 41 | May 14, 2026 | ||
| Depth Completion | NYU v2 (val) | 41 | Feb 26, 2026 | ||
| Natural Language Visual Reasoning | NLVR2 | 41 | Apr 21, 2026 | ||
| Closed-set Source-Free Domain Adaptation | Office-31 (target) | 41 | Apr 21, 2026 | ||
| Motion-to-text retrieval | KIT-ML (test) | 41 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | MotorImagery | 41 | May 4, 2026 | ||
| Semantic Segmentation | CityScapes | 41 | Jun 16, 2026 | ||
| Web agent tasks | Mind2Web Cross-Domain | 41 | Jun 9, 2026 | ||
| Segmentation | ACDC | 41 | Mar 24, 2026 | ||
| Out-of-Distribution Detection | ImageNet (ID) vs Places365 (OOD) 1.0 (test) | 41 | Feb 27, 2026 |