Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 618 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Human Pose Estimation | Human3.6M standard (test) | 37 | Apr 7, 2026 | ||
| Image Classification | ImageNet (val) | 37 | Feb 26, 2026 | ||
| Blond Hair classification | CelebA (test) | 37 | May 7, 2026 | ||
| 5-way Few-shot Classification | ChestX | 37 | Mar 6, 2026 | ||
| 5-way Few-shot Classification | Crop Diseases | 37 | Mar 6, 2026 | ||
| 5-way Few-shot Classification | Plantae | 37 | Mar 6, 2026 | ||
| Temporal Action Detection | FineAction | 37 | Mar 6, 2026 | ||
| Question Answering | RelExt MRQA out-of-domain evaluation | 37 | Mar 12, 2026 | ||
| Question Answering | TextbookQA MRQA out-of-domain evaluation | 37 | Mar 12, 2026 | ||
| Text-to-Image Generation | COCO 256 x 256 2014 (val) | 37 | Feb 26, 2026 | ||
| Object Detection | Cityscapes S -> C adaptation (val) | 37 | Feb 26, 2026 | ||
| Semantic Segmentation | Cityscapes (val) | 37 | Feb 26, 2026 | ||
| Entity Recognition | CORD official (test) | 37 | Feb 26, 2026 | ||
| Object Detection | MS COCO (train val) | 37 | Feb 26, 2026 | ||
| Person Re-identification | VC-Clothes general (all cams) | 37 | Mar 4, 2026 | ||
| 6 DoF Pose Estimation | YCB-V BOP challenge 2020 | 37 | Feb 26, 2026 | ||
| Relation Extraction | TACRED v1.0 (test) | 37 | Feb 26, 2026 | ||
| Image Harmonization | HAdobe5k iHarmony4 (test) | 37 | Feb 26, 2026 | ||
| Trajectory Prediction | ETH-UCY ZARA1 | 37 | May 22, 2026 | ||
| Image Super-Resolution (x2) | Set14 | 37 | Jun 19, 2026 | ||
| Monocular 3D Object Detection | KITTI car category (val) | 37 | Mar 19, 2026 | ||
| Salient Object Detection | DUTS 5019 (test) | 37 | Jul 7, 2026 | ||
| Aspect-based Sentiment Classification | Lap14 | 37 | Feb 26, 2026 | ||
| Semantic Entity Recognition | FUNSD (test) | 37 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 50% symmetric label noise | 37 | Apr 23, 2026 |