Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 251 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Monocular Depth Estimation | KITTI improved ground truth (Eigen split) | 65 | Feb 26, 2026 | ||
| Human Pose Estimation | COCO (val) | 65 | Jul 2, 2026 | ||
| Image Classification | ImageNet 1K (val) | 65 | Feb 26, 2026 | ||
| Instance Segmentation | MS-COCO | 65 | Mar 16, 2026 | ||
| Image Classification | CIFAR10 (train) | 65 | May 26, 2026 | ||
| Multilingual Question Answering | TydiQA | 65 | Mar 12, 2026 | ||
| Visual Question Answering | VizWiz (test-dev) | 65 | Feb 27, 2026 | ||
| Link Prediction | UCI (inductive) | 65 | May 18, 2026 | ||
| Image Classification | ImageNet | 65 | Mar 16, 2026 | ||
| Image Classification | STL10-LT (gamma_l = 10) (test) | 65 | May 19, 2026 | ||
| Few-Shot Semantic Segmentation | Pascal-5i (test) | 65 | Feb 26, 2026 | ||
| Category-level 6D Pose Estimation | REAL275 (test) | 65 | Jul 7, 2026 | ||
| Image Classification | ImageNet original (val) | 65 | Feb 26, 2026 | ||
| Out-of-distribution Detection | ImageNet-1k vs Textures (test) | 65 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10-LT (val) | 65 | Feb 26, 2026 | ||
| Anomaly Detection | MNIST (test) | 65 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym halfcheetah-medium | 65 | May 29, 2026 | ||
| Image Classification | ImageNet 1k (val) | 65 | Feb 26, 2026 | ||
| Node Classification | Crocodile | 65 | Jun 11, 2026 | ||
| 3D Shape Correspondence | FAUST remeshed (test) | 65 | Feb 26, 2026 | ||
| Facial Landmark Detection | WFLW (Full) | 65 | Feb 26, 2026 | ||
| Image classification | VLCS (test) | 65 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 (test) | 65 | Feb 26, 2026 | ||
| Semantic Segmentation | BDD100K night | 65 | Feb 26, 2026 | ||
| Relation Extraction | DocRED v1 (dev) | 65 | Feb 26, 2026 |