Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 922 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Spectral Clustering | Letters | 29 | Feb 26, 2026 | ||
| Spectral Clustering | USPS | 29 | Feb 26, 2026 | ||
| Spectral Clustering | PenDigits | 29 | Feb 26, 2026 | ||
| Super-Resolution | Sun80 | 29 | Feb 26, 2026 | ||
| Video Object Segmentation | DAVIS 2016 (test) | 29 | Feb 26, 2026 | ||
| Document classification | R52 (test) | 29 | Feb 26, 2026 | ||
| Link Prediction | USAir | 29 | Feb 26, 2026 | ||
| Trajectory Prediction | HOTEL v1.0 (test) | 29 | Feb 26, 2026 | ||
| 3D Human Mesh Recovery | Human3.6M (Protocol 2) | 29 | Feb 26, 2026 | ||
| Text Classification | SST binary | 29 | Feb 26, 2026 | ||
| Image Classification | Imbalanced CIFAR-10 long-tailed, ratio 10 (test) | 29 | Feb 26, 2026 | ||
| Image Classification | ImageNet Long-Tailed (test) | 29 | Feb 26, 2026 | ||
| Facial Landmark Detection | 300-W public Full inter-pupil normalization (test) | 29 | Feb 26, 2026 | ||
| Action Recognition | UCF101 (1) | 29 | Feb 26, 2026 | ||
| Review Sentiment Classification | IMDB (test) | 29 | Feb 26, 2026 | ||
| Thoracic Pathology Classification | ChestX-ray14 2017 (test) | 29 | Feb 26, 2026 | ||
| Semantic Role Labeling | CoNLL WSJ 2005 (test) | 29 | Feb 26, 2026 | ||
| Task-oriented Dialogue | Stanford Multi-Domain Dialogue (SMD) (test) | 29 | Feb 26, 2026 | ||
| Object Counting | COCO Count (test) | 29 | Feb 26, 2026 | ||
| Question Generation | SQuAD 1.1 (test) | 29 | Feb 26, 2026 | ||
| Multi-label Image Classification | NUS-WIDE 81 concept labels (test) | 29 | Feb 26, 2026 | ||
| 2D vehicle detection | KITTI (test) | 29 | Feb 26, 2026 | ||
| Visual Grounding | Flickr30k Entities (test) | 29 | Feb 26, 2026 | ||
| Clustering | CMU-PIE | 29 | Feb 26, 2026 | ||
| Anomaly Detection | NAB (test) | 29 | Jun 24, 2026 |