Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1087 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR-10C level 5 (test) | 26 | Feb 26, 2026 | ||
| Image-level Anomaly Detection | Mvtec LOCO AD | 26 | Feb 26, 2026 | ||
| Action Recognition | H2O (test) | 26 | Feb 26, 2026 | ||
| Blind Image Quality Assessment | CLIVE (test) | 26 | Feb 26, 2026 | ||
| Vehicle Re-identification | VehicleID | 26 | May 7, 2026 | ||
| Skeleton-based action recognition | PKU-MMD Phase I (cross-subject) | 26 | Feb 26, 2026 | ||
| Object Detection | OV-LVIS v1 (val) | 26 | Apr 28, 2026 | ||
| Open-Vocabulary Object Detection | LVIS | 26 | May 26, 2026 | ||
| Image Retrieval | CUB-200 (test) | 26 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | UEA Multivariate Time Series Classification Archive | 26 | May 13, 2026 | ||
| Time Series Anomaly Detection | UEA CT | 26 | Apr 1, 2026 | ||
| Graph Classification | COLLAB (10-fold cross val) | 26 | Feb 27, 2026 | ||
| Semantic Segmentation | Cityscapes (val) | 26 | Mar 30, 2026 | ||
| Information Retrieval | MS MARCO DL2019 | 26 | Feb 26, 2026 | ||
| Science Question Answering | ARC Easy | 26 | Feb 26, 2026 | ||
| Action segmentation | HOI4D official (test) | 26 | Jun 2, 2026 | ||
| Traveling Salesman Problem | Euclidean TSP N=50 | 26 | Feb 26, 2026 | ||
| Image Classification | iWILDCam OOD | 26 | Feb 26, 2026 | ||
| Visual Localization | ScanNet Indoor (test) | 26 | Mar 24, 2026 | ||
| Semantic Segmentation | COCO-20i 5-shot | 26 | Feb 26, 2026 | ||
| Pose Estimation | ScanNet 1500 (test) | 26 | Feb 26, 2026 | ||
| Single Image Desnowing | CSD 2000 (test) | 26 | Feb 26, 2026 | ||
| 3D Object Detection | nuScenes Nighttime (val) | 26 | Feb 26, 2026 | ||
| Text Classification | HSOL | 26 | Feb 26, 2026 | ||
| Named Entity Recognition | OntoNotes Onto-C 5.0 | 26 | Feb 26, 2026 |