Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1774 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Summarization | EMAILSUM long 1.0 (test) | 19 | Feb 26, 2026 | ||
| Summarization | EMAILSUM short 1.0 (test) | 19 | Feb 26, 2026 | ||
| Machine Translation | WMT19 English-German (En-De) (test) | 19 | Feb 26, 2026 | ||
| Video Grounding | TACOS | 19 | Feb 26, 2026 | ||
| Toxicity detection | CivilComments-WILDS (test) | 19 | Feb 26, 2026 | ||
| Abstractive Question Summarization | MEQSUM 1.0 (test) | 19 | Feb 26, 2026 | ||
| Node Classification | ogbn-mag v1 (val) | 19 | Feb 26, 2026 | ||
| Node Classification | ogbn-products transductive (test) | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | Mapillary Vistas full (val) | 19 | Feb 26, 2026 | ||
| Time-series Classification | Epilepsy (test) | 19 | Apr 23, 2026 | ||
| Visual Question Answering | PathVQA (test) | 19 | Feb 26, 2026 | ||
| Image Classification | LabelMe (test) | 19 | Feb 26, 2026 | ||
| Node Classification | Coauthor CS (semi-supervised transductive) | 19 | Feb 26, 2026 | ||
| Normal Estimation | ModelNet40 (test) | 19 | Feb 26, 2026 | ||
| Generative Modeling | CIFAR10 (test) | 19 | Feb 26, 2026 | ||
| Causal Discovery | Sachs real data d=11 | 19 | May 28, 2026 | ||
| Natural Language Inference | CB val (test) | 19 | Feb 26, 2026 | ||
| Document-level Relation Extraction | GDA (test) | 19 | Feb 26, 2026 | ||
| Discontinuous Named Entity Recognition | CADEC (test) | 19 | Feb 26, 2026 | ||
| Multi-turn Dialogue Reasoning | MuTual (test) | 19 | Jun 4, 2026 | ||
| Out-of-distribution detection | ImageNet-A | 19 | Apr 13, 2026 | ||
| Human Pose Estimation | COCO-C (val) | 19 | Feb 26, 2026 | ||
| Video Super-Resolution | REDS4 BI degradation v1.0 (test) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 60% symmetric noise (test) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 40% symmetric noise (test) | 19 | Feb 26, 2026 |