Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1959 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Instruction Following | SCAN jump | 18 | Feb 26, 2026 | ||
| Triple Classification | UMLS | 18 | Mar 6, 2026 | ||
| Table-to-Text Generation | CATS (dev) | 18 | Feb 26, 2026 | ||
| Model Inversion Attack | CelebA | 18 | Jun 2, 2026 | ||
| Unsupervised Online Label Shift | MNIST | 18 | Feb 26, 2026 | ||
| Image Denoising | McMaster 2011 (test) | 18 | Feb 26, 2026 | ||
| Binary temporal relation classification | TRACIE, MATRES, and TODAY (test) | 18 | Feb 26, 2026 | ||
| Attribute Extraction | 30PT (test) | 18 | Feb 26, 2026 | ||
| Machine Translation | Multi30k En-Cs 2018 (test) | 18 | Mar 4, 2026 | ||
| Machine Translation | Multi30k En-Cs 2016 (test) | 18 | Mar 4, 2026 | ||
| Stylized Machine Translation | MSMT Average (test) | 18 | Jul 2, 2026 | ||
| OOD Detection | ImageNet-O | 18 | Feb 26, 2026 | ||
| Identifying plausible explanations | δ-ATOMIC | 18 | Apr 28, 2026 | ||
| Document-level Event Argument Extraction | RAMS (dev) | 18 | Feb 26, 2026 | ||
| Attribute Clustering | WOAM 1.0 (test) | 18 | Feb 26, 2026 | ||
| Named Entity Recognition | ATIS target | 18 | Feb 26, 2026 | ||
| Feature Attribution | SST2 | 18 | Feb 26, 2026 | ||
| Feature Attribution | IMDB (test) | 18 | Feb 26, 2026 | ||
| Feature Attribution | Rotten Tomatoes fine-tuned | 18 | Feb 26, 2026 | ||
| Speech Translation | MuST-C En-De (test) | 18 | Feb 26, 2026 | ||
| User Intent Detection | ChattyChef (test) | 18 | Feb 26, 2026 | ||
| Simultaneous Machine Translation | IWSLT En-De 2014 (test) | 18 | Feb 26, 2026 | ||
| Simultaneous Machine Translation | IWSLT Vi-En 2015 | 18 | Feb 26, 2026 | ||
| Machine Translation Quality Estimation | WMT News 2020 (test) | 18 | Feb 26, 2026 | ||
| Adversarial Attack on Deepfake Detectors | FF++ (test) | 18 | Feb 26, 2026 |