Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 445 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Word alignment | Buckeye | 45 | Jul 9, 2026 | ||
| Mathematical Reasoning | MATH 500 | 45 | Jun 17, 2026 | ||
| Mathematical Reasoning | Math-Synth | 45 | Jun 17, 2026 | ||
| Traffic Prediction | PeMS04 to PeMS08 | 45 | Jun 16, 2026 | ||
| Conformal Prediction | Example 2 5-class data (a=0.5, Easy Bin, r* > 0.5) synthetic (test) | 45 | Jun 16, 2026 | ||
| Conformal Prediction | Example 2 5-class data (a=0.5, Hard Bin, r* <= 0.5) synthetic (test) | 45 | Jun 16, 2026 | ||
| Conformal Prediction | 5-class synthetic data Example 1, Easy Bin r* > 0.5 | 45 | Jun 16, 2026 | ||
| Magnetic flux profile prediction | D3D-ITER (test) | 45 | Jun 16, 2026 | ||
| Magnetic flux profile prediction | KSTAR (test) | 45 | Jun 16, 2026 | ||
| Magnetic flux profile prediction | SPHER (test) | 45 | Jun 16, 2026 | ||
| Rare-disease diagnosis | CROSSRARE-BENCH RareBench cohort 1.0 (test) | 45 | Jun 15, 2026 | ||
| Image Classification | CIFAR-100 | 45 | Jun 15, 2026 | ||
| Referential Instructions | Navigation Environments (test) | 45 | Jun 11, 2026 | ||
| Forecasting | Weather | 45 | Jun 9, 2026 | ||
| Human Preference Ranking | Arena Human Preference 140K | 45 | Jun 9, 2026 | ||
| Sycophancy Mitigation | Anthropic Model-Written Evals | 45 | Jun 5, 2026 | ||
| Topology Optimization | heat conduction dataset (test) | 45 | Jun 5, 2026 | ||
| Topology Optimization | heat conduction dataset | 45 | Jun 5, 2026 | ||
| Topology Optimization | mechanical dataset | 45 | Jun 5, 2026 | ||
| Denoising | IRIS Lab (Subject8) | 45 | Jun 5, 2026 | ||
| Image Denoising | IRIS Lab Subject7 | 45 | Jun 5, 2026 | ||
| Image Denoising | IRIS Lab database Subject1 | 45 | Jun 5, 2026 | ||
| Image Denoising | IRIS Lab database Subject6 | 45 | Jun 5, 2026 | ||
| Image Denoising | IRIS Subject2 | 45 | Jun 5, 2026 | ||
| Image Denoising | IRIS Lab database Subject5 | 45 | Jun 5, 2026 |