Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 716 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Forgetting Rate | 20News FR | 34 | Feb 26, 2026 | ||
| Node Classification | snap-patents | 34 | Feb 26, 2026 | ||
| Multi-label classification | VOC-MLT (test) | 34 | Feb 26, 2026 | ||
| Action localization | THUMOS14 | 34 | Feb 26, 2026 | ||
| Clustering | IMDB | 34 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 1.0 (test) | 34 | Feb 26, 2026 | ||
| Multi-Object Tracking | MOT 2017 (test) | 34 | Feb 26, 2026 | ||
| Depth Completion | VOID (test) | 34 | May 29, 2026 | ||
| Classification | activity | 34 | Feb 26, 2026 | ||
| Object Detection | Pascal VOC Class Split 1 2007 (test) | 34 | Feb 26, 2026 | ||
| Image Classification | ImageNet LT 2018 (test) | 34 | Feb 26, 2026 | ||
| Aspect Sentiment Triplet Extraction | Rest SemEval 2016 (test) | 34 | Feb 26, 2026 | ||
| Pixel-level Manipulation Detection | COVER | 34 | Feb 27, 2026 | ||
| Pixel-level Manipulation Detection | Columbia | 34 | Feb 27, 2026 | ||
| Pixel-level Manipulation Detection | NIST | 34 | Feb 27, 2026 | ||
| Extreme Classification | LF-AmazonTitles 1.3M | 34 | Jun 25, 2026 | ||
| Domain Adaptation | MNIST to SVHN (test) | 34 | Jun 4, 2026 | ||
| End-to-End Text Spotting | SCUT-CTW1500 (test) | 34 | Feb 26, 2026 | ||
| Camera Pose Estimation | TUM freiburg1 | 34 | Feb 26, 2026 | ||
| Skeleton Action Recognition | NTU-120 (96/24 random split) | 34 | Apr 13, 2026 | ||
| Action Recognition | NTU-60 (Cross-Subject (CS)) | 34 | Jun 26, 2026 | ||
| Node Property Prediction | ogbn-proteins (test) | 34 | Feb 26, 2026 | ||
| Few-shot image classification | tieredImageNet standard (test) | 34 | Feb 26, 2026 | ||
| Deepfake Detection | FF++ | 34 | Feb 26, 2026 | ||
| Video Prediction | BAIR | 34 | Feb 26, 2026 |