Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 329 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero/Few-shot Language Modeling | Standard Downstream Tasks (arc-c, arc-e, boolq, hellaswag, piqa, siqa, winogrande) | 55 | Mar 4, 2026 | ||
| Zero-shot Classification | 5 zero-shot tasks | 55 | Jun 1, 2026 | ||
| Reasoning | GSM8K | 55 | May 27, 2026 | ||
| Action Recognition | HMDB-51 | 55 | May 25, 2026 | ||
| Image Quality Assessment | TID 2013 | 55 | May 19, 2026 | ||
| Question Answering | ARC Easy | 55 | Jun 2, 2026 | ||
| Salient Object Detection | DUT-O | 55 | Jul 1, 2026 | ||
| Commonsense Reasoning | HellaSwag | 55 | Mar 20, 2026 | ||
| High-resolution perception | V* | 55 | Jul 8, 2026 | ||
| Automatic Speech Recognition | AISHELL-1 | 55 | May 28, 2026 | ||
| Audio Question Answering | MMAR | 55 | Jun 9, 2026 | ||
| Natural Language Understanding | GLUE | 55 | Mar 26, 2026 | ||
| Offline Reinforcement Learning | OGBench antmaze-large-navigate-singletask task1-v0 to task5-v0 | 55 | Feb 26, 2026 | ||
| Robotic Manipulation | LIBERO-Goal | 55 | Jun 30, 2026 | ||
| Outlier Detection | Breastw | 55 | May 12, 2026 | ||
| Membership Inference Attack | ArXiv | 55 | Apr 23, 2026 | ||
| Unlearning | MUSE-News 1.0 (test) | 55 | Mar 31, 2026 | ||
| Anomaly Detection | Glass | 55 | Jun 16, 2026 | ||
| Tabular Anomaly Detection | Optdigits | 55 | May 12, 2026 | ||
| Time Series Anomaly Detection | MSL | 55 | Jun 18, 2026 | ||
| PDE Solving | Poisson | 55 | May 8, 2026 | ||
| Mathematical Reasoning | MATH 500 | 55 | Mar 6, 2026 | ||
| Long document retrieval | LongBench Retrieval v2 (full) | 55 | Feb 26, 2026 | ||
| Video Understanding | TempCompass MCQ (test) | 55 | Mar 31, 2026 | ||
| Image Classification | CIFAR-100 LT (IF=100) | 55 | Jul 8, 2026 |