Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 661 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| In-hospital mortality prediction | MIMIC-III | 36 | Jun 9, 2026 | ||
| Camera Tracking | TUM RGB-D | 36 | May 14, 2026 | ||
| Image Reconstruction | FFHQ (test) | 36 | May 26, 2026 | ||
| Domain Generalization | DomainNet (test) | 36 | Jun 16, 2026 | ||
| Action Recognition | UCF101 base-to-new | 36 | Feb 26, 2026 | ||
| Few-shot Image Classification | SUN397 | 36 | Mar 12, 2026 | ||
| Few-Shot Segmentation | MS COCO | 36 | Feb 26, 2026 | ||
| Trajectory Prediction | Zara2 | 36 | May 26, 2026 | ||
| 3D Object Detection | Waymo Open 100% (val) | 36 | Feb 26, 2026 | ||
| Semantic Scene Completion | SemanticKITTI hidden (test) | 36 | Apr 8, 2026 | ||
| Domain Generalization | CIFAR-100-C | 36 | Feb 26, 2026 | ||
| Domain Generalization | CIFAR-10-C | 36 | Feb 26, 2026 | ||
| Novel View Synthesis | Blender Synthetic 8-view (test) | 36 | Feb 26, 2026 | ||
| OOD Detection | CIFAR-10 | 36 | May 21, 2026 | ||
| Temporal Action Localization | ActivityNet 1.2 (test) | 36 | Feb 26, 2026 | ||
| Image Classification | STL-10 | 36 | Feb 26, 2026 | ||
| Code Generation | APPS (test) | 36 | Jun 23, 2026 | ||
| Unsupervised Classification | FieldGuide-2 (test) | 36 | Feb 26, 2026 | ||
| Information Retrieval | SciFact BEIR (test) | 36 | May 27, 2026 | ||
| Image Classification | DomainBed v1.0 (test) | 36 | Feb 26, 2026 | ||
| Image Classification | ImageNet-10 | 36 | Feb 26, 2026 | ||
| Image Classification | ICinW 20 datasets 1.0 (test) | 36 | Feb 26, 2026 | ||
| Relation Extraction | DocRED human-annotated (test) | 36 | Feb 26, 2026 | ||
| Image Captioning | NoCaps | 36 | Feb 27, 2026 | ||
| Super-Resolution | Colon | 36 | Jun 26, 2026 |