Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1092 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Action Segmentation | Breakfast 14 | 26 | Feb 26, 2026 | ||
| 3D Object Detection | KITTI (test) | 26 | Feb 27, 2026 | ||
| Image Denoising | DND 60 (test) | 26 | Feb 26, 2026 | ||
| Image Deraining | Average across Deraining Datasets (test) | 26 | Feb 26, 2026 | ||
| Disentanglement | MPI3D (test) | 26 | Apr 21, 2026 | ||
| Image Classification | ImageNet 1000 (val) | 26 | Feb 26, 2026 | ||
| Class-Incremental Learning | CIFAR-100 (incremental) | 26 | Feb 26, 2026 | ||
| Partial Person Re-identification | Partial-iLIDS (test) | 26 | Feb 26, 2026 | ||
| Video Action Recognition | Kinetics-400 v1 (test) | 26 | Feb 26, 2026 | ||
| Object Detection | VOC 2007 | 26 | May 13, 2026 | ||
| Ad-hoc Video Search | TRECVID (TV18) 2018 (test) | 26 | Feb 26, 2026 | ||
| Multi-Task Learning | NYU v2 | 26 | Mar 10, 2026 | ||
| Node Classification | Yelp (test) | 26 | Feb 26, 2026 | ||
| Violence Detection | Crowd Violence | 26 | Mar 31, 2026 | ||
| Trajectory Forecasting | TrajNet Challenge | 26 | Feb 26, 2026 | ||
| 2D Depth Estimation | ScanNet | 26 | Feb 26, 2026 | ||
| Named Entity Recognition | WNUT 2016 (test) | 26 | Feb 26, 2026 | ||
| Coherence classification | GCDC 1.0 (test) | 26 | Feb 26, 2026 | ||
| Image classification | ImageNet 9 (val) | 26 | Feb 26, 2026 | ||
| Stereo Matching | KITTI 2012 (All split) | 26 | Feb 26, 2026 | ||
| Stereo Matching | KITTI 2012 (Noc) | 26 | Feb 26, 2026 | ||
| Automatic Speech Recognition | AISHELL (test) | 26 | May 11, 2026 | ||
| Abstractive Summarization | WikiHow | 26 | Feb 26, 2026 | ||
| Unsupervised image segmentation | COCO-Stuff (test) | 26 | Feb 26, 2026 | ||
| Domain Generalization | PACS 23 (test) | 26 | Feb 26, 2026 |