Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 585 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Face Recognition | CelebA (test) | 39 | Feb 26, 2026 | ||
| Text Detection | SCUT-CTW1500 | 39 | Feb 26, 2026 | ||
| Image Classification | VTAB v2 (test) | 39 | Feb 26, 2026 | ||
| Lip Reading | LRS2 (test) | 39 | Jun 2, 2026 | ||
| Natural Language Inference | Natural Language Inference (NLI) (test) | 39 | Apr 28, 2026 | ||
| Sampling | CIFAR-10 | 39 | Feb 26, 2026 | ||
| Multi-source Domain Adaptation | PACS | 39 | Apr 28, 2026 | ||
| Image Classification | KMNIST | 39 | Jun 23, 2026 | ||
| Multi-person pose estimation | PoseTrack 2017 (test) | 39 | Feb 26, 2026 | ||
| Multi-person pose estimation | PoseTrack 2017 (val) | 39 | Feb 26, 2026 | ||
| instanceOf triple classification | YAGO39K (test) | 39 | Mar 10, 2026 | ||
| Video Summarization | TVSum Canonical | 39 | Feb 26, 2026 | ||
| Data-to-text generation | WebNLG (test) | 39 | Feb 27, 2026 | ||
| Machine Translation | WMT14 English-French (newstest2014) | 39 | Feb 26, 2026 | ||
| Image Classification | STL to CIFAR standard (test) | 39 | Feb 26, 2026 | ||
| Image Classification | ImageNet (val) | 39 | Feb 26, 2026 | ||
| Grammatical Error Correction | CoNLL 2014 | 39 | Feb 26, 2026 | ||
| Grasp Detection | Cornell Dataset (object-wise) | 39 | Feb 26, 2026 | ||
| Semantic Textual Similarity | STS 2014 | 39 | May 29, 2026 | ||
| One-shot segmentation | Cluttered Omniglot one-shot | 39 | Feb 26, 2026 | ||
| Perceptual Similarity | BAPPS (val) | 39 | Feb 26, 2026 | ||
| Machine Translation | WMT16 German-English (test) | 39 | Feb 26, 2026 | ||
| Molecular Property Classification | MoleculeNet ClinTox | 39 | May 14, 2026 | ||
| Human Parsing | LIP | 39 | Feb 26, 2026 | ||
| Open-domain question answering | SQUAD Open (test) | 39 | Feb 26, 2026 |