Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 683 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | Vision Datasets 20 tasks 1.0 (test) | 35 | May 29, 2026 | ||
| Safety Performance | JBB | 35 | Mar 4, 2026 | ||
| Multivariate distribution estimation | Synthetic Data I | 35 | Feb 26, 2026 | ||
| Cell type classification | VISp cell_types_25 (test) | 35 | Feb 26, 2026 | ||
| Open door | Meta-World | 35 | Feb 26, 2026 | ||
| Outlier Detection | Arrhythmia | 35 | Jun 16, 2026 | ||
| Structure-based drug design | CrossDocked 2020 | 35 | Jun 2, 2026 | ||
| Sleep Stage Classification | SleepEDF-20 | 35 | May 19, 2026 | ||
| GP regression | Kernel Cookbook 1.0 (test) | 35 | Feb 26, 2026 | ||
| Question Answering | WinoGrande, HellaSwag, ARC-e, ARC-c, PIQA Average | 35 | Feb 26, 2026 | ||
| Time Series Forecasting | Daily Gold Price | 35 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Hopper medium-expert | 35 | May 29, 2026 | ||
| Knowledge | GPQA | 35 | Mar 4, 2026 | ||
| Long-context evaluation | RULER 8k | 35 | Feb 27, 2026 | ||
| Long-context evaluation | RULER 4k | 35 | Jul 3, 2026 | ||
| Node Classification | WikiCS (test) | 35 | Jul 1, 2026 | ||
| Multimodal Recommendation | Pet | 35 | May 19, 2026 | ||
| Collaborative Filtering | Amazon-Book | 35 | Feb 26, 2026 | ||
| Sequential Recommendation | Amazon Instruments (test) | 35 | Mar 30, 2026 | ||
| Sequential Recommendation | Amazon CDs and Vinyl (test) | 35 | May 15, 2026 | ||
| Recommendation | Steam | 35 | Jun 4, 2026 | ||
| 3D Reconstruction | GSO | 35 | Jul 2, 2026 | ||
| Polyp Segmentation | CVC-ClinicDB (seen) | 35 | Apr 21, 2026 | ||
| Polyp Segmentation | Kvasir-SEG (seen) | 35 | Apr 21, 2026 | ||
| Polyp Segmentation | CVC-ColonDB (unseen) | 35 | Apr 21, 2026 |