Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2255 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Coherence evaluation | HarmBench (test) | 16 | Feb 26, 2026 | ||
| Vehicle Routing Problem | VRP 500 Customers (100 instances) | 16 | Feb 26, 2026 | ||
| Image Classification | OxfordIIITPet | 16 | Apr 24, 2026 | ||
| Ant | MuJoCo | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM-8K | 16 | Apr 9, 2026 | ||
| Time Series Forecasting | ELC | 16 | Feb 26, 2026 | ||
| Scientific Reasoning | Materials | 16 | Apr 3, 2026 | ||
| Scientific Reasoning | Physics | 16 | Apr 3, 2026 | ||
| Scientific Reasoning | Chemistry | 16 | Apr 3, 2026 | ||
| Ranking Recommendation | TikTok Live | 16 | Feb 26, 2026 | ||
| Semantic Segmentation | Cityscapes | 16 | Feb 26, 2026 | ||
| Time Series Forecasting | TimeMMD Social Good | 16 | May 12, 2026 | ||
| Classification | COMPAS (test) | 16 | Jul 1, 2026 | ||
| Machine Unlearning | CLEAR (test 2) | 16 | Feb 26, 2026 | ||
| Machine Unlearning | CLEAR (test 1) | 16 | Feb 26, 2026 | ||
| Contributor Attribution | ArtBench Post-Impressionism | 16 | Feb 26, 2026 | ||
| Contributor Attribution | CIFAR-20 (test) | 16 | Feb 26, 2026 | ||
| Math Reasoning | Open-RS | 16 | Feb 26, 2026 | ||
| Math Reasoning | LIMR | 16 | Feb 26, 2026 | ||
| Attention Mechanism Latency Benchmark | Synthetic sequences | 16 | Feb 26, 2026 | ||
| Machine Unlearning | MUSE | 16 | Feb 26, 2026 | ||
| Probabilistic time series forecasting | ENTSO-e Load FEV leaderboard subset 1H | 16 | Feb 26, 2026 | ||
| Autoregressive PDE rollout | CE-RM (test) | 16 | Feb 26, 2026 | ||
| Data Assimilation | ERA5 2022-01-03 06 UTC snapshot v1 (test) | 16 | Feb 26, 2026 | ||
| Anomaly Detection | WPBC | 16 | Feb 26, 2026 |