Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1338 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Machine Translation | En -> De (test) | 23 | Feb 26, 2026 | ||
| Document Classification | Yahoo Answers | 23 | Feb 26, 2026 | ||
| Speech Emotion Recognition | SAVEE | 23 | Feb 26, 2026 | ||
| Dependency Parsing | Dep. Parse (test) | 23 | Feb 26, 2026 | ||
| Character-level language modeling | Enwik8 (val) | 23 | Jun 24, 2026 | ||
| Caption Retrieval | Flickr30k | 23 | Feb 26, 2026 | ||
| Sequential Recommendation | Amazon Games (test) | 23 | Feb 26, 2026 | ||
| Relation Extraction | SCIERC (test) | 23 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | ITOP top-view | 23 | Feb 26, 2026 | ||
| Machine Translation | IWSLT English-Vietnamese 2015 (tst2013) | 23 | Feb 26, 2026 | ||
| Sentiment Classification | Yelp original 2013 (test) | 23 | Feb 26, 2026 | ||
| Sequence Tagging | CoNLL 2003 (test) | 23 | Feb 26, 2026 | ||
| Aerial-to-Ground Image Synthesis | CVUSA | 23 | Feb 26, 2026 | ||
| Forward Synthesis | SMolInstruct | 23 | Jun 23, 2026 | ||
| Node Classification | PubMed (10-fold) | 23 | Feb 26, 2026 | ||
| Natural Language Inference | MultiNLI matched (dev) | 23 | Feb 26, 2026 | ||
| Domain Adaptation (Classification) | USPS to MNIST | 23 | Feb 26, 2026 | ||
| Semantic Role Labeling | CoNLL 2012 (dev) | 23 | Feb 26, 2026 | ||
| Face Recognition | CASIA NIR-VIS Standard Protocol 2.0 (test) | 23 | Feb 26, 2026 | ||
| Audio Super-Resolution | Piano (test) | 23 | Feb 26, 2026 | ||
| Person Identity Classification | Extended Yale B (test) | 23 | Feb 26, 2026 | ||
| Relation Extraction | NYT-Freebase (test) | 23 | Feb 26, 2026 | ||
| Face Verification | YouTube Face (YTF) 40 (10-fold cross-validation) | 23 | Feb 26, 2026 | ||
| Visual Tracking | OTB 2015 (full) | 23 | Feb 26, 2026 | ||
| Aspect-level sentiment classification | Restaurant | 23 | Feb 26, 2026 |