Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 518 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node Classification | Chameleon (fixed) | 42 | Feb 26, 2026 | ||
| Node Classification | Squirrel (fixed) | 42 | Feb 26, 2026 | ||
| Machine Translation | WMT En-Fr 2014 | 42 | Feb 26, 2026 | ||
| Image Classification | Colored-MNIST (CMNIST) | 42 | Feb 26, 2026 | ||
| Medical Image Segmentation | CHD 68 patients total (test) | 42 | Feb 26, 2026 | ||
| Semantic Textual Similarity | STS16 (test) | 42 | Mar 25, 2026 | ||
| Semantic Textual Similarity | STS15 (test) | 42 | Mar 25, 2026 | ||
| Semantic Textual Similarity | STS14 (test) | 42 | Mar 25, 2026 | ||
| Semantic Textual Similarity | STS13 (test) | 42 | Mar 25, 2026 | ||
| Video Question Answering | MSR-VTT | 42 | Feb 27, 2026 | ||
| Micro-gesture recognition | iMiGUE (test) | 42 | Jun 9, 2026 | ||
| Dataset Comparison | Isolet (test) | 42 | Feb 26, 2026 | ||
| Dataset Comparison | Mnist-r (test) | 42 | Feb 26, 2026 | ||
| MRI Reconstruction | fastMRI 4X acceleration (test) | 42 | May 13, 2026 | ||
| Argument Identification and Classification | ERE-EN (test) | 42 | Feb 26, 2026 | ||
| Image-to-text Retrieval | MSCOCO (5K) | 42 | May 8, 2026 | ||
| Stereo Image Super-Resolution | Middlebury | 42 | Feb 26, 2026 | ||
| Stereo Image Super-Resolution | KITTI 2012 | 42 | Feb 26, 2026 | ||
| Out-of-distribution Detection | Places365 (Out-of-distribution) vs CIFAR-100 (In-distribution) | 42 | Jul 8, 2026 | ||
| Semantic segmentation | Semantic3D (reduced-8) | 42 | Mar 30, 2026 | ||
| Depth Map Super-Resolution | RGB-D-D (test) | 42 | Mar 24, 2026 | ||
| Visual Object Tracking | LaSOT 1.0 (test) | 42 | Feb 26, 2026 | ||
| Unsupervised Domain Adaptation | VisDA Synthetic to Real 2017 | 42 | Feb 26, 2026 | ||
| Face Forgery Detection | FaceForensics++ | 42 | May 29, 2026 | ||
| License Plate Recognition | EnglishLP (test) | 42 | Feb 26, 2026 |