Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 462 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| RGB-D Salient Object Detection | STERE (test) | 45 | Feb 26, 2026 | ||
| Facial Landmark Detection | WFLW Illumination | 45 | Feb 26, 2026 | ||
| Facial Landmark Detection | WFLW Expression | 45 | Feb 26, 2026 | ||
| Image Generation | CelebA-HQ (test) | 45 | May 15, 2026 | ||
| Multimodal Multiclass Classification | FOOD-101 (test) | 45 | Feb 26, 2026 | ||
| AMR Parsing | AMR 1.0 (test) | 45 | Feb 26, 2026 | ||
| Passage retrieval | Natural Questions (NQ) (test) | 45 | Jun 30, 2026 | ||
| Few-shot Image Classification | CropDiseases CDFSL (test) | 45 | Feb 26, 2026 | ||
| Video Super-resolution | SPMCS (test) | 45 | Mar 30, 2026 | ||
| Reinforcement Learning | Atari 2600 MONTEZUMA'S REVENGE | 45 | Feb 26, 2026 | ||
| Machine Reading Comprehension | DRCD (test) | 45 | Feb 26, 2026 | ||
| Machine Reading Comprehension | DRCD (dev) | 45 | Feb 26, 2026 | ||
| Facial Action Unit Detection | DISFA (test) | 45 | Apr 13, 2026 | ||
| Image Classification | Clothing1M 1.0 (test) | 45 | Feb 26, 2026 | ||
| Multi-document Summarization | Multi-News (test) | 45 | Feb 26, 2026 | ||
| Question Answering | HotpotQA distractor (dev) | 45 | Feb 26, 2026 | ||
| Pedestrian trajectory prediction | Hotel | 45 | Feb 26, 2026 | ||
| Pedestrian trajectory prediction | ETH | 45 | Feb 26, 2026 | ||
| Phase classification | Penn Action (test) | 45 | Feb 26, 2026 | ||
| Classification | VisDA 2017 (val) | 45 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (test) | 45 | Apr 1, 2026 | ||
| 6D Object Pose Estimation | OccludedLINEMOD (test) | 45 | Feb 26, 2026 | ||
| Action Recognition | Northwestern-UCLA (NUCLA) Multiview (cross-view) | 45 | Feb 26, 2026 | ||
| Image Retrieval | Paris6k | 45 | Feb 26, 2026 | ||
| Scene Graph Classification | Visual Genome | 45 | Feb 27, 2026 |