Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 533 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Clustering | Tiny-ImageNet (test) | 41 | Feb 26, 2026 | ||
| Panoptic Segmentation | COCO 2017 (test-dev) | 41 | Feb 26, 2026 | ||
| Classification | Splice | 41 | May 12, 2026 | ||
| Machine Translation | WMT English-French 2014 (test) | 41 | Feb 27, 2026 | ||
| Salient Object Detection | DUT (test) | 41 | Feb 26, 2026 | ||
| Video Semantic Segmentation | CamVid | 41 | Mar 26, 2026 | ||
| Sentiment Analysis | SST-2 (dev) | 41 | Feb 26, 2026 | ||
| Node classification | Coauthor Phy (test) | 41 | Feb 26, 2026 | ||
| Scene Text Recognition | ICDAR 2015 | 41 | Jun 2, 2026 | ||
| Video Classification | UCF-101 (test) | 41 | Feb 26, 2026 | ||
| Video Super-Resolution | REDS4 (val) | 41 | Feb 26, 2026 | ||
| 5-way Few-shot Image Classification | tieredImageNet 5-shot (test) | 41 | Feb 26, 2026 | ||
| Span-based Semantic Role Labeling | CoNLL 2005 (Out-of-domain (Brown)) | 41 | Feb 26, 2026 | ||
| 6D Pose Estimation | LineMod (test) | 41 | Jun 23, 2026 | ||
| Semantic Role Labeling | CoNLL 2005 (WSJ) | 41 | Feb 27, 2026 | ||
| Temporal Action Proposal Generation | THUMOS 14 | 41 | Feb 26, 2026 | ||
| Multi-person 3D Pose Estimation | MuPoTS-3D (test) | 41 | Feb 26, 2026 | ||
| Object Detection | MS COCO 2014 (val) | 41 | Feb 26, 2026 | ||
| Optical Flow Estimation | KITTI 2012 (test) | 41 | Feb 26, 2026 | ||
| Generalized Zero-Shot Learning | AWA | 41 | Feb 26, 2026 | ||
| Object Classification | ModelNet40 | 41 | Mar 4, 2026 | ||
| Review Sentiment Classification | Yelp 2014 (test) | 41 | Feb 26, 2026 | ||
| Unsupervised Domain Adaptation | SVHN -> MNIST (test) | 41 | Feb 26, 2026 | ||
| 3D Shape Classification | ModelNet-40 | 41 | Feb 26, 2026 | ||
| Clustering | YTF | 41 | Apr 7, 2026 |