Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1968 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sentiment Classification | SST-2 (OOD) | 18 | Feb 26, 2026 | ||
| Sentiment Classification | SemEval 2017 (OOD) | 18 | Feb 26, 2026 | ||
| Sentiment Classification | IMDb (In-domain) | 18 | Feb 26, 2026 | ||
| 3D Object Detection | S3DIS | 18 | Feb 26, 2026 | ||
| Claim Verification | DIALFACT (val) | 18 | Feb 26, 2026 | ||
| Claim Verification | DIALFACT (test) | 18 | Feb 26, 2026 | ||
| Hallucination Detection | FOIL | 18 | Feb 26, 2026 | ||
| Aerial Object Detection | HRSC 2016 | 18 | Mar 18, 2026 | ||
| Image Classification | ImageNet | 18 | Feb 26, 2026 | ||
| Class-incremental learning | 5-datasets (test) | 18 | Feb 26, 2026 | ||
| Object Detection | PASCAL VOC (VOC07 labeled + VOC12 + COCO20cls unlabeled) | 18 | Feb 26, 2026 | ||
| Face Super-Resolution | CelebA-HQ 1024x1024 (test) | 18 | Feb 26, 2026 | ||
| LiDAR-based Panoptic Segmentation | SemanticKITTI 1.0 (test) | 18 | Feb 26, 2026 | ||
| Image Inpainting | CelebA v1 (test) | 18 | Feb 26, 2026 | ||
| Machine Translation | IWSLT17 En-Fr (test) | 18 | Feb 26, 2026 | ||
| Smiling Classification | CelebA (test) | 18 | Feb 26, 2026 | ||
| Text-to-image synthesis | MSCOCO (test) | 18 | Feb 26, 2026 | ||
| Script Reasoning | Script Reasoning | 18 | Feb 26, 2026 | ||
| Cross-domain continual learning | OfficeHome unseen domains | 18 | Feb 26, 2026 | ||
| Cross-domain continual learning | DomainNet unseen domains | 18 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 42 (test) | 18 | Feb 26, 2026 | ||
| Image Classification | Waterbirds 95% (test) | 18 | May 14, 2026 | ||
| Image Classification | STL-10 (train test) | 18 | Feb 26, 2026 | ||
| Table Structure Recognition | SciTSR | 18 | Apr 20, 2026 | ||
| Classification | Places 205 | 18 | May 6, 2026 |