Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 667 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Classification | SHD | 36 | Mar 17, 2026 | ||
| Mental state decoding | HCP (test) | 36 | Feb 26, 2026 | ||
| Cardiac Segmentation | ACDC-C (unseen test) | 36 | Feb 26, 2026 | ||
| Regression | Friedman 10 | 36 | Feb 26, 2026 | ||
| Regression | Friedman 5 | 36 | Feb 26, 2026 | ||
| Regression | Neal | 36 | Feb 26, 2026 | ||
| PDE Solving | Klein-Gordon equation | 36 | Jul 3, 2026 | ||
| Forward PDE solving | Plasticity | 36 | Jun 1, 2026 | ||
| Forward PDE solving | Airfoil | 36 | Jun 1, 2026 | ||
| Risk-constrained optimization | Fractional knapsack problems synthetic simulation (test) | 36 | Feb 26, 2026 | ||
| Risk-constrained optimization | Fractional knapsack problems synthetic simulation 500 trials (test) | 36 | Feb 26, 2026 | ||
| Shortest path optimization | Shortest path problem 5x5 grid (test) | 36 | Feb 26, 2026 | ||
| PDE Modeling | Burgers' Equation various resolutions (val) | 36 | Feb 26, 2026 | ||
| Motion Segmentation | Hopkins 155 2-motion sequences | 36 | Jun 5, 2026 | ||
| Regression | MoleculeNet (scaffold) | 36 | Apr 29, 2026 | ||
| Long-term forecasting | ETTh2 v1 (test) | 36 | Apr 30, 2026 | ||
| Node classification | Genius | 36 | May 13, 2026 | ||
| Link Sign Prediction | Epinions | 36 | Feb 26, 2026 | ||
| Instance Segmentation | MitoEM-H Rat -> Human (test) | 36 | May 4, 2026 | ||
| Molecular property prediction | MOLPCBA OGB (test) | 36 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC Original protocol 1464 labeled images | 36 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | DTD | 36 | Feb 26, 2026 | ||
| Lane Segmentation | BDD100K v1.0 (test) | 36 | Feb 26, 2026 | ||
| Reliability of post-edit LLMs | Pile-CC | 36 | Feb 27, 2026 | ||
| Reliability of post-edit LLMs | Wikipedia | 36 | Feb 27, 2026 |