Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1359 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Agentic tool-use | Agentic Macro-aggregate | 22 | May 7, 2026 | ||
| Reading Comprehension | Reading Macro-aggregate | 22 | May 7, 2026 | ||
| Knowledge retrieval | Knowledge Macro-aggregate | 22 | May 7, 2026 | ||
| Code and Software Engineering | Code/SE Macro-aggregate | 22 | May 7, 2026 | ||
| Math problem solving | Math Macro-aggregate | 22 | May 7, 2026 | ||
| Multiple-choice Query Answering | PersonaMem (Average) | 22 | May 7, 2026 | ||
| Medical Image Segmentation | Abdominal Atlas | 22 | May 7, 2026 | ||
| Harmfulness Evaluation | Mousetrap | 22 | May 7, 2026 | ||
| Harmfulness Evaluation | AutoRAN | 22 | May 7, 2026 | ||
| Harmfulness Evaluation | PAIR | 22 | May 21, 2026 | ||
| Harmfulness Evaluation | GCG | 22 | May 7, 2026 | ||
| Utility Evaluation | MATH500 | 22 | May 7, 2026 | ||
| Utility Evaluation | GPQA Diamond | 22 | May 7, 2026 | ||
| Utility Evaluation | MMLU | 22 | May 7, 2026 | ||
| Time Series Forecasting | ETTm2 | 22 | Jun 15, 2026 | ||
| Time Series Forecasting | ETTm1 | 22 | Jun 15, 2026 | ||
| Image Classification | ImageNet Nette | 22 | May 6, 2026 | ||
| Classification | MNIST+# | 22 | May 6, 2026 | ||
| Classification | DeepLesion+# | 22 | May 6, 2026 | ||
| Classification | HAM10000+ | 22 | May 6, 2026 | ||
| Agentic Task Completion | τ2-bench Airline | 22 | Jun 4, 2026 | ||
| Robotic Manipulation | RoboCasa Kitchen | 22 | May 29, 2026 | ||
| Long-context language modeling | InfiniteBench | 22 | Jun 11, 2026 | ||
| Gaze Estimation | ETH-XGaze | 22 | May 4, 2026 | ||
| Science Question Answering | SQA | 22 | Jun 2, 2026 |