Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 171 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Few-shot Text Classification | 26 few-shot tasks Class -> Class transfer setting (test) | 84 | Feb 26, 2026 | ||
| Membership Inference Attack | WikiMIA length 64 | 84 | Apr 1, 2026 | ||
| Image Quality Assessment | AGIQA 3K (test) | 84 | Feb 26, 2026 | ||
| OOD detection | SVHN (test) | 84 | Mar 30, 2026 | ||
| 3D Object Detection | TJ4DRadSet (test) | 84 | Jun 11, 2026 | ||
| OOD Detection | LSUN-Resize (OOD) with CIFAR-10 (ID) (test) | 84 | Jul 8, 2026 | ||
| Question Answering | HeadQA | 84 | Jul 3, 2026 | ||
| Semantic Segmentation | BDD100K (val) | 84 | Mar 24, 2026 | ||
| Video-to-Text Retrieval | VATEX | 84 | May 27, 2026 | ||
| Multi-person motion prediction | ExPI (common action split) | 84 | Feb 26, 2026 | ||
| Image Compressed Sensing | Set5 | 84 | Feb 26, 2026 | ||
| Efficiency analysis | Long-Range Arena (LRA) | 84 | Feb 26, 2026 | ||
| Gait Recognition | Gait3D | 84 | Apr 15, 2026 | ||
| Natural Language Understanding | SuperGLUE | 84 | Feb 26, 2026 | ||
| Video Classification | Kinetics-600 (val) | 84 | Jun 25, 2026 | ||
| Cross-view geo-localization | CVUSA | 84 | Mar 30, 2026 | ||
| Stereo Matching | Middlebury | 84 | Jul 9, 2026 | ||
| Temporal Action Proposal Generation | THUMOS14 (test) | 84 | Feb 27, 2026 | ||
| Graph Classification | ogbg-molhiv | 84 | Jun 2, 2026 | ||
| Stereo Matching | Scene Flow (test) | 84 | May 12, 2026 | ||
| Action Recognition | Kinetics-600 (test) | 84 | Feb 26, 2026 | ||
| Visual Question Answering | TextVQA v1.0 (val) | 84 | Mar 24, 2026 | ||
| Semantic Segmentation | Mapillary Vistas (val) | 84 | Mar 24, 2026 | ||
| Knowledge Base Completion | YAGO3-10 (test) | 84 | Jun 1, 2026 | ||
| Machine Translation | WMT Ro-En 2016 (test) | 84 | Mar 31, 2026 |