Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1335 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | iNaturalist 2019 (test) | 23 | Feb 26, 2026 | ||
| Aspect Sentiment Triplet Extraction | R14 2014 (test) | 23 | Apr 13, 2026 | ||
| Long-tailed Image Classification | CIFAR100-LT imbalance factor 100 (test) | 23 | Feb 26, 2026 | ||
| Classification | DomainNet | 23 | May 12, 2026 | ||
| 3D Left Atrium Segmentation | LA database 16 labeled scans v1 (20% labeled) | 23 | Feb 26, 2026 | ||
| 3D Left Atrium Segmentation | LA database 8 scans v1 (10% labeled) | 23 | Feb 26, 2026 | ||
| Prostate Segmentation | PROMISE12 (test) | 23 | Feb 26, 2026 | ||
| Object Detection | HRSC 2016 | 23 | Mar 4, 2026 | ||
| Skeleton Action Recognition | NTU-60 (55/5 random split) | 23 | Apr 13, 2026 | ||
| Fact Verification | FEVER 1.0 (dev) | 23 | Feb 26, 2026 | ||
| Video Interpolation | HQF DAVIS240 1 frame skip (all sequences) | 23 | Feb 26, 2026 | ||
| Human Pose Estimation | COCO keypoint (val) | 23 | Feb 26, 2026 | ||
| Named Entity Recognition | Twitter NER | 23 | Apr 23, 2026 | ||
| Node Classification | Coauthor CS (semi-supervised inductive) | 23 | Feb 26, 2026 | ||
| Classification | PhysioNet | 23 | Feb 26, 2026 | ||
| Paraphrase Detection | PAWS original (test) | 23 | Feb 26, 2026 | ||
| Case Decision Prediction | ILDC multi | 23 | Feb 26, 2026 | ||
| Image Classification | ImageNet (val) | 23 | Feb 26, 2026 | ||
| Scene Flow Estimation | KITTIo (test) | 23 | Feb 26, 2026 | ||
| Logical Reasoning | ReClor v1 (test) | 23 | Feb 26, 2026 | ||
| Text Classification | AG | 23 | Jun 4, 2026 | ||
| Stereo Matching | ETH3D (train) | 23 | Feb 26, 2026 | ||
| Node Classification | AIRPORT | 23 | May 4, 2026 | ||
| Anomaly Detection | TAD (test) | 23 | Apr 28, 2026 | ||
| Hyperspectral Image Classification | Salinas Scene (10% train) | 23 | Mar 4, 2026 |