Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 982 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | Pascal-5i | 28 | Feb 26, 2026 | ||
| Multi-label Few-Shot Learning | FewAsp single (test) | 28 | Feb 26, 2026 | ||
| Multi-label Few-Shot Learning | FewAsp multi 1.0 (test) | 28 | Feb 26, 2026 | ||
| Few-shot Image Classification | mini-Cars (test) | 28 | Feb 26, 2026 | ||
| Chinese Spelling Check | SIGHAN14 (test) | 28 | Feb 26, 2026 | ||
| Out-of-distribution Detection | LSUN (Out-of-distribution) vs CIFAR-10 (In-distribution) | 28 | Feb 26, 2026 | ||
| Scene Flow Estimation | KITTI (test) | 28 | Feb 26, 2026 | ||
| Action Recognition | NTU-120 1.0 (Cross-Subject 1 (CS1)) | 28 | Feb 26, 2026 | ||
| Link Prediction | ogbl-wikikg2 v1 (test) | 28 | Feb 26, 2026 | ||
| Video Recognition | FCVID (test) | 28 | Feb 26, 2026 | ||
| Aspect-based Sentiment Classification | Rest SemEval-2016 (test) | 28 | Apr 16, 2026 | ||
| Depth Map Super-Resolution | NYU v2 (test) | 28 | Feb 26, 2026 | ||
| 2D Depth Estimation | 7-Scenes | 28 | May 15, 2026 | ||
| Image-text retrieval | MSCOCO (test) | 28 | Mar 27, 2026 | ||
| Facial Expression Recognition | AffectNet (test) | 28 | Feb 26, 2026 | ||
| Logical Reasoning | ReClor Easy (test) | 28 | Feb 26, 2026 | ||
| Knowledge Base Question Answering | MetaQA 1hop | 28 | Feb 26, 2026 | ||
| RST Parsing | RST-DT original Parseval (test) | 28 | Feb 26, 2026 | ||
| Action Recognition | Breakfast | 28 | Feb 26, 2026 | ||
| Video Action Recognition | UCF101 5-way 5-shot | 28 | Feb 26, 2026 | ||
| Video Action Recognition | HMDB51 5-way 5-shot | 28 | Feb 26, 2026 | ||
| One-class classification | CIFAR-10 | 28 | Feb 26, 2026 | ||
| Pose Estimation | COCO (test) | 28 | Feb 26, 2026 | ||
| Disentanglement | Shapes3D (test) | 28 | Apr 21, 2026 | ||
| Page-level retrieval | KILT (test) | 28 | Feb 27, 2026 |