Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 821 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR-10 10% labeled data (test) | 31 | Jun 25, 2026 | ||
| Multi-Task Learning | NYU v2 (test) | 31 | Feb 26, 2026 | ||
| Object Detection | LVIS Mini v1.0 (val) | 31 | Feb 26, 2026 | ||
| Semantic Segmentation | RELLIS-3D | 31 | Mar 31, 2026 | ||
| Video Prediction | Caltech Pedestrian 10 -> 1 (test) | 31 | Feb 26, 2026 | ||
| Robustness Evaluation | SI-Score size synthetic | 31 | Feb 26, 2026 | ||
| Robustness Evaluation | SI-Score rotation synthetic | 31 | Feb 26, 2026 | ||
| Robustness Evaluation | SI-Score location synthetic | 31 | Feb 26, 2026 | ||
| Video Question Answering | MSRVTT-MC (test) | 31 | Feb 26, 2026 | ||
| Semi-supervised node classification | Citeseer | 31 | Feb 26, 2026 | ||
| Semantic Segmentation | PASCAL VOC 1/8 subset 2012 (val) | 31 | Feb 26, 2026 | ||
| Claim Verification | HoVer (test) | 31 | Apr 2, 2026 | ||
| Image Manipulation Localization | NIST 16 | 31 | Feb 26, 2026 | ||
| Unconditional Image Synthesis | FFHQ 256x256 (test) | 31 | Feb 26, 2026 | ||
| Visual Entailment | SNLI-VE | 31 | Jun 19, 2026 | ||
| Link Prediction | ICEWS 05-15 | 31 | May 11, 2026 | ||
| Semantic Entity Recognition | FUNSD | 31 | Feb 26, 2026 | ||
| Node Classification | Pubmed (48/32/20) | 31 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | 3DPW cross-dataset (test) | 31 | Apr 9, 2026 | ||
| Open-Partial-Set Domain Adaptation | Office-Home | 31 | Feb 26, 2026 | ||
| Few-shot image classification | FC100 | 31 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Maze2D | 31 | Apr 15, 2026 | ||
| Domain Generalization | PACS OOD (test) | 31 | May 27, 2026 | ||
| Graph Classification | COLLAB Social TU (10-fold cross val) | 31 | Mar 19, 2026 | ||
| Credit Risk Prediction | German Credit (test) | 31 | Feb 26, 2026 |