Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 492 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | HotpotQA (dev) | 43 | May 19, 2026 | ||
| Image Classification | ImageNet 1k (val) | 43 | Feb 26, 2026 | ||
| Cross-lingual Language Understanding | XTREME | 43 | Mar 10, 2026 | ||
| Violence Detection | Hockey Fight | 43 | Mar 31, 2026 | ||
| RGB Saliency Detection | LFSD (test) | 43 | Feb 26, 2026 | ||
| Video Paragraph Captioning | ActivityNet Captions ae (val) | 43 | Feb 26, 2026 | ||
| RGBD Saliency Detection | LFSD | 43 | Feb 26, 2026 | ||
| Few-shot classification | Omniglot 20-way 5-shot (test) | 43 | Feb 26, 2026 | ||
| Few-shot classification | Omniglot 20-way 1-shot (test) | 43 | Feb 26, 2026 | ||
| Depth Completion | NYU-Depth v2 | 43 | Mar 17, 2026 | ||
| Aspect-based Sentiment Analysis | Laptop dataset | 43 | May 22, 2026 | ||
| Video Question Answering | TVQA (test-public) | 43 | Feb 26, 2026 | ||
| Visual Localization | Aachen Day-Night (day) | 43 | Jul 3, 2026 | ||
| Story Ending Generation | ROCStories (test) | 43 | Feb 26, 2026 | ||
| Image Quality Estimation | LIVE (test) | 43 | Feb 26, 2026 | ||
| Node Classification | PPI | 43 | May 8, 2026 | ||
| Entity Linking | AIDA A | 43 | Feb 26, 2026 | ||
| Face Recognition | MegaFace (set1) | 43 | Feb 26, 2026 | ||
| 3D Object Detection | KITTI official (test) | 43 | Feb 26, 2026 | ||
| Keypoint Detection | MS COCO 2017 (test-dev) | 43 | Feb 26, 2026 | ||
| Node Classification | Cora 2% label rate | 43 | Mar 4, 2026 | ||
| Crowd Counting | UCF_CC_50 (5-fold cross-validation) | 43 | Feb 26, 2026 | ||
| Machine Translation | WMT En-De (newstest2014) | 43 | Feb 26, 2026 | ||
| Single Image Super-Resolution | Set5 x2 scale (test) | 43 | Feb 26, 2026 | ||
| Image Denoising | 68 natural images (test) | 43 | Feb 26, 2026 |