Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 952 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Web Agent Navigation | TimeWarp Wiki Environment v1:6 | 28 | Mar 6, 2026 | ||
| Hallucination Evaluation | COCO | 28 | Mar 6, 2026 | ||
| Intellectual Property Protection | Office-31 | 28 | Mar 6, 2026 | ||
| Time to First Token | Llama 3.1 8B Q4 weights | 28 | Mar 6, 2026 | ||
| Nuclei Segmentation | PanNuke T2 | 28 | Mar 6, 2026 | ||
| Nuclei Segmentation | PanNuke T1 | 28 | Mar 6, 2026 | ||
| Procedure Planning | COIN | 28 | Jun 16, 2026 | ||
| Image Classification | CIFAR-100 ID (test) | 28 | May 4, 2026 | ||
| Radiology Report Generation | Radiology Reports | 28 | Mar 5, 2026 | ||
| Face Privacy Protection | LADN-Dataset | 28 | Jul 1, 2026 | ||
| Face Privacy Protection | CelebA-HQ | 28 | Jul 1, 2026 | ||
| Mathematical Reasoning | Omni-MATH | 28 | Mar 5, 2026 | ||
| Reasoning | Combined 37 Tasks (test) | 28 | Mar 5, 2026 | ||
| Reasoning | Combined 107 Tasks (train) | 28 | Mar 5, 2026 | ||
| Reasoning | Reasoning-Gym (test) | 28 | Mar 5, 2026 | ||
| Reasoning | SymBench (test) | 28 | Mar 5, 2026 | ||
| Reasoning | Reasoning-Gym (train) | 28 | Mar 5, 2026 | ||
| Reasoning | SymBench (train) | 28 | Mar 5, 2026 | ||
| Raw Image Reconstruction | NUS dataset | 28 | Jun 24, 2026 | ||
| 2D Segmentation | ISIC 2017 | 28 | Apr 7, 2026 | ||
| Multi-Turn Problem Solving | KMP-FQA | 28 | Mar 4, 2026 | ||
| Classification | FGVC Aircraft | 28 | Jun 16, 2026 | ||
| Cross-view geo-localization | University-1652 Drone to Satellite 1.0 | 28 | May 13, 2026 | ||
| Cross-Domain Recommendation | Douban Movie → Book | 28 | Jun 25, 2026 | ||
| Long-context reasoning | OOLONG trec_coarse | 28 | Mar 18, 2026 |