Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1519 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | A2D2 (test) | 21 | Feb 26, 2026 | ||
| Grounded Situation Recognition | SWiG v1 (dev) | 21 | Feb 26, 2026 | ||
| Reinforcement Learning | Atari 57 | 21 | Feb 26, 2026 | ||
| Object Localization | CUB-200 (test) | 21 | Feb 26, 2026 | ||
| Multi-Object Tracking | MOT16 1.0 (test) | 21 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K 10 | 21 | Feb 26, 2026 | ||
| Link Prediction | FB122 (test) | 21 | Feb 26, 2026 | ||
| Aspect extraction and sentiment classification | 15res | 21 | Feb 26, 2026 | ||
| Link Prediction | WN18 Inductive (test) | 21 | Feb 26, 2026 | ||
| Dialogue-based Multiple-choice Question Answering | DREAM (test) | 21 | Feb 26, 2026 | ||
| Machine Translation | WMT'16 Romanian-English (Ro-En) (test) | 21 | May 29, 2026 | ||
| Question Generation | SQuAD 1.1 | 21 | Feb 27, 2026 | ||
| Single-label activity classification | Breakfast | 21 | Feb 26, 2026 | ||
| Clustering | CARS 196 (test) | 21 | Feb 26, 2026 | ||
| Named Entity Recognition | BC2GM local evaluation (test) | 21 | Feb 26, 2026 | ||
| 1-shot classification | tiered-ImageNet (test) | 21 | Feb 26, 2026 | ||
| Weakly supervised object localization | CUB200-2011 | 21 | Feb 26, 2026 | ||
| 3D Multi-person Pose Estimation | MuPoTS-3D | 21 | Feb 26, 2026 | ||
| Monocular Depth Estimation | KITTI 2012 2015 (Eigen split) | 21 | Feb 26, 2026 | ||
| Image Classification | Animals with Attributes (AwA) (Standard Split) | 21 | Feb 26, 2026 | ||
| Zero-shot Image Classification | aPY (test) | 21 | Feb 26, 2026 | ||
| Email Subject Line Generation | AESLC (test) | 21 | Feb 26, 2026 | ||
| Email Subject Line Generation | AESLC (dev) | 21 | Feb 26, 2026 | ||
| Node Classification | NELL (test) | 21 | Feb 26, 2026 | ||
| Recommendation | Book-crossing (test) | 21 | May 11, 2026 |