Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1964 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-Class Classification | Cover Type (CovType) (test) | 18 | Feb 26, 2026 | ||
| Arithmetic Reasoning | SingleEq (test) | 18 | Jun 26, 2026 | ||
| Table-to-Text Generation | LOGICNLG (test) | 18 | Feb 26, 2026 | ||
| Coreference Resolution | Winograd | 18 | Mar 13, 2026 | ||
| Language Modeling | Lambada | 18 | Apr 10, 2026 | ||
| Out-of-domain Image Classification | DomainNet (out-of-domain) | 18 | Feb 26, 2026 | ||
| Out-of-domain Image Classification | TerraIncognita (out-of-domain) | 18 | Feb 26, 2026 | ||
| Out-of-domain Image Classification | Office-Home (out-of-domain) | 18 | Feb 26, 2026 | ||
| Brain MRI Registration | IXI atlas-to-patient | 18 | Feb 26, 2026 | ||
| Brain MRI Registration | JHU inter-patient | 18 | Feb 26, 2026 | ||
| WSI Classification | TCGA-RCC | 18 | Feb 26, 2026 | ||
| Molecule property prediction | ogbg-SIDER | 18 | Feb 26, 2026 | ||
| Molecule property prediction | ogbg-Tox21 | 18 | Feb 26, 2026 | ||
| Molecule property prediction | ogbg-ToxCast | 18 | Feb 26, 2026 | ||
| Polymer property prediction | O2Perm | 18 | Feb 26, 2026 | ||
| Polymer property prediction | PolyDensity | 18 | Feb 26, 2026 | ||
| Polymer property prediction | MeltingTemp | 18 | Feb 26, 2026 | ||
| Polymer property prediction | GlassTemp | 18 | Feb 26, 2026 | ||
| Visual Sound Source Localization | Flickr SoundNet (test) | 18 | Feb 26, 2026 | ||
| Abductive Reasoning | ART (Abductive Reasoning in NLP) (test) | 18 | Apr 28, 2026 | ||
| Disentangled representation learning | MPI3D | 18 | Feb 26, 2026 | ||
| Disentangled representation learning | Shapes3D | 18 | Feb 26, 2026 | ||
| Face Forgery Detection | FaceShifter (test) | 18 | May 29, 2026 | ||
| Image Classification | CIFAR-100 | 18 | Feb 26, 2026 | ||
| Multi-Agent Reinforcement Learning | SMAC maps | 18 | Feb 26, 2026 |