Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1192 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME24 search | 24 | May 11, 2026 | ||
| Machine Unlearning | PACS Sketch (OOD) | 24 | May 11, 2026 | ||
| Writing | WildChat 5,000 conversations | 24 | May 11, 2026 | ||
| Coding | WildChat 5,000 conversations | 24 | May 11, 2026 | ||
| Safety Verification | Dubins Car subregions certifiable | 24 | May 11, 2026 | ||
| Science Experiment Execution | ScienceWorld (test) | 24 | May 11, 2026 | ||
| Household Task Execution | AlfWorld (test) | 24 | May 11, 2026 | ||
| Embodied AI task execution | EmbodiedBench EB-ALFRED | 24 | May 11, 2026 | ||
| Interpretable Graph Classification | MUTAGENICITY | 24 | May 11, 2026 | ||
| Interpretable Graph Classification | BENZENE | 24 | May 11, 2026 | ||
| Interpretable Graph Classification | 3MR | 24 | May 11, 2026 | ||
| Class-Incremental Learning | Tiny-ImageNet | 24 | May 11, 2026 | ||
| 3D Reconstruction | Moving Checkerboard (test) | 24 | May 11, 2026 | ||
| Mathematical Reasoning | WeMath 525 samples | 24 | May 11, 2026 | ||
| Robotic manipulation | LIBERO Object | 24 | Jul 7, 2026 | ||
| Mathematical Reasoning | Average of Mathematical Reasoning Benchmarks | 24 | May 11, 2026 | ||
| Reasoning | SuperGPQA | 24 | May 11, 2026 | ||
| Reasoning | MMLU-Pro | 24 | May 11, 2026 | ||
| Reasoning | ARC Challenge | 24 | May 11, 2026 | ||
| Height Estimation | Satellite Surface Reconstruction IAPRA & JAX scenes | 24 | May 11, 2026 | ||
| Appearance Reconstruction | Satellite Surface Reconstruction IAPRA & JAX scenes | 24 | May 11, 2026 | ||
| Preference Alignment | UltraFeedback | 24 | Jun 4, 2026 | ||
| Sample-level Membership Inference | LIBERO Long | 24 | May 11, 2026 | ||
| Pruning Accuracy Retention | CIFAR-100 (test) | 24 | May 11, 2026 | ||
| ECG Classification | CinC Georgia (test) | 24 | May 11, 2026 |