Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 369 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| General Text Question Answering | HotpotQA | 51 | May 11, 2026 | ||
| Keyword Spotting | LibriPhrase Easy (LPE) | 51 | Jun 11, 2026 | ||
| Robotic Manipulation | SIMPLER Visual Matching WidowX robot | 51 | Apr 8, 2026 | ||
| Clustering | Glass | 51 | Jun 25, 2026 | ||
| Time Series Forecasting | Traffic | 51 | Apr 14, 2026 | ||
| Code Generation | LiveCodeBench | 51 | Mar 9, 2026 | ||
| Language Modeling | FineWeb-Edu (val) | 51 | Jun 1, 2026 | ||
| Out-of-Distribution Detection | CIFAR-100 OpenOOD (test) | 51 | May 28, 2026 | ||
| Temporal Information Retrieval | Temporal Nobel Prize (TNP) | 51 | Feb 26, 2026 | ||
| Multimodal Recommendation | Sports Amazon (test) | 51 | May 4, 2026 | ||
| AI Image Detection | Midjourney | 51 | Mar 4, 2026 | ||
| Pose estimation | KITTI odometry | 51 | Feb 27, 2026 | ||
| Depth Completion | NYU v2 | 51 | Jul 7, 2026 | ||
| Few-Shot Segmentation | ISIC 2018 | 51 | May 20, 2026 | ||
| Image Classification | 14 Tasks Merge | 51 | Feb 26, 2026 | ||
| Communication overhead measurement | Private vector-wise filtering setup phase | 51 | Feb 26, 2026 | ||
| Few-shot Learning | LongBench | 51 | Mar 13, 2026 | ||
| Summarization | LongBench | 51 | Mar 13, 2026 | ||
| General Reasoning | MMLU | 51 | May 25, 2026 | ||
| Mathematical Reasoning | GSM8K 4-shot | 51 | Jun 26, 2026 | ||
| General Question Answering | PopQA | 51 | Apr 10, 2026 | ||
| Multi-Hop Question Answering | Bamboogle | 51 | Mar 10, 2026 | ||
| Code Generation | HumanEval | 51 | Feb 26, 2026 | ||
| Embodied decision-making | ALFWorld | 51 | Jun 15, 2026 | ||
| Knowledge | GPQA | 51 | Mar 31, 2026 |