Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 822 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node classification | genius (test) | 31 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | 3DPW OCC (test) | 31 | Feb 26, 2026 | ||
| Keyword Extraction | SemEval 2010 | 31 | Feb 26, 2026 | ||
| Unconditional Image Generation | ImageNet 32 | 31 | Feb 26, 2026 | ||
| Target Aspect Sentiment Detection | Rest 2016 | 31 | Mar 4, 2026 | ||
| Action Recognition | Penn Action | 31 | Mar 19, 2026 | ||
| Medical Image Segmentation | JSRT (test) | 31 | Feb 26, 2026 | ||
| Cross-lingual Summarization | En2ZhSum (test) | 31 | Feb 26, 2026 | ||
| Word Alignment | RWTH Gold Alignment de-en (test) | 31 | Feb 26, 2026 | ||
| Semantic Segmentation | IDD | 31 | Jun 2, 2026 | ||
| Color Constancy | NUS-8 (three-fold cross val) | 31 | Feb 26, 2026 | ||
| Dependency Parsing | PTB | 31 | Mar 19, 2026 | ||
| Multimodal Machine Translation | Multi30k En-Fr 2017 (test) | 31 | Feb 26, 2026 | ||
| Summarization | CNNDM (test) | 31 | Apr 7, 2026 | ||
| Video Super-Resolution | UDM10 BD degradation (test) | 31 | Feb 26, 2026 | ||
| Video Super-Resolution | Vid4 BI degradation (test) | 31 | Feb 27, 2026 | ||
| Action segmentation | Breakfast (test) | 31 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 SVHN in-distribution out-of-distribution standard (test) | 31 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal-VOC Disjoint 15-5 2012 | 31 | Feb 26, 2026 | ||
| RGB-D Salient Object Detection | DES (test) | 31 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | CIFAR10 vs. SVHN | 31 | Apr 13, 2026 | ||
| Landmark Detection | COFW-68 (test) | 31 | Feb 26, 2026 | ||
| Super-Resolution | DIV2KRK Scale x4 Setting 2 (test) | 31 | Feb 26, 2026 | ||
| Machine Translation | WMT newstest 2016 (test) | 31 | Feb 26, 2026 | ||
| Node Classification | Pubmed (60/20/20 random split) | 31 | Feb 26, 2026 |