Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 665 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Named Entity Recognition | ACE04 (test) | 36 | Feb 26, 2026 | ||
| Video Super-Resolution | Vid4 4x upscaling (Calendar, City, Foliage, Walk) | 36 | Feb 26, 2026 | ||
| Entity Disambiguation | AIDA-CONLL (test) | 36 | Feb 26, 2026 | ||
| Trajectory Prediction | Argoverse (test) | 36 | Mar 10, 2026 | ||
| Image Classification | Mini-ImageNet (val) | 36 | Feb 26, 2026 | ||
| Instance-level search | ROxford (test) | 36 | Feb 26, 2026 | ||
| Data-to-text generation | E2E | 36 | Feb 27, 2026 | ||
| MRI Reconstruction | fastMRI Knee (test) | 36 | Jun 2, 2026 | ||
| Bird's Eye View Detection | KITTI (val) | 36 | Feb 26, 2026 | ||
| Visual Object Tracking | VOT 2018 | 36 | May 27, 2026 | ||
| Incremental Semantic Segmentation | Pascal-VOC 2012 (val) | 36 | Feb 26, 2026 | ||
| Action Recognition | EPIC-Kitchens (val) | 36 | Feb 26, 2026 | ||
| Link Prediction | Kinship | 36 | Feb 26, 2026 | ||
| Graph Matching | PASCAL VOC with Berkeley annotations (test) | 36 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 Long-Tailed 1.0 (test) | 36 | Feb 26, 2026 | ||
| Word Sense Disambiguation | SemEval-2007 Task 17 (test) | 36 | Feb 26, 2026 | ||
| Multivariate Time Series Forecasting | Exchange Rate | 36 | Feb 26, 2026 | ||
| Node Classification | PubMed 0.05% labels | 36 | Feb 26, 2026 | ||
| Entity Alignment | DWY100K DBP-WD | 36 | Feb 26, 2026 | ||
| Few-shot Relation Classification | FewRel 1.0 (test) | 36 | Feb 26, 2026 | ||
| 3D Action Recognition | NTU RGB+D 60 (Cross-View) | 36 | Apr 29, 2026 | ||
| Answer Ranking | TREC QA (train) | 36 | Feb 26, 2026 | ||
| Node-level classification | USA | 36 | Jun 9, 2026 | ||
| Graph Classification | D&D (test) | 36 | Feb 26, 2026 | ||
| Point Cloud Registration | ModelNet40 (Unseen categories) | 36 | Feb 27, 2026 |