Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2075 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Desnowing | Realistic | 17 | Feb 26, 2026 | ||
| Grammatical Error Correction | FCGEC (test) | 17 | Feb 26, 2026 | ||
| Natural Language Understanding | SuperGLUE RoBERTa-large (test) | 17 | Feb 26, 2026 | ||
| Classification | HumSet XLM-RBASE (test) | 17 | Feb 26, 2026 | ||
| Multilingual Multi-label Text Classification | HumSet (test) | 17 | Feb 26, 2026 | ||
| Arithmetic Tree Generation | 128-bit Adder | 17 | Feb 26, 2026 | ||
| Sleep Stage Classification | Sleep-EDFX from SHHS | 17 | May 11, 2026 | ||
| Sign Language Recognition | Phoenix 2014 (test) | 17 | Feb 26, 2026 | ||
| Multi-label Classification | MIRFLICKR | 17 | Mar 4, 2026 | ||
| Vision-Language Probing | VL-CheckList (test) | 17 | Feb 26, 2026 | ||
| Super-Resolution | AIM (val) | 17 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL MuJoCo walker2d medium v2 | 17 | Mar 10, 2026 | ||
| Offline Reinforcement Learning | D4RL MuJoCo walker2d random v2 | 17 | Mar 10, 2026 | ||
| Knowledge Graph Reasoning | UMLS (test) | 17 | Feb 26, 2026 | ||
| Interactive Segmentation | PartImageNet | 17 | Feb 26, 2026 | ||
| Interactive Segmentation | PascalPart | 17 | Feb 26, 2026 | ||
| Trajectory Prediction | GTA-1M (test) | 17 | Feb 26, 2026 | ||
| Trajectory Prediction | GIMO (test) | 17 | Feb 26, 2026 | ||
| Landmark Detection | ISBI Challenge 2015 (test) | 17 | May 6, 2026 | ||
| Object Detection | HRSC2016 | 17 | Mar 16, 2026 | ||
| Human Dance Generation | TikTok (test) | 17 | Feb 26, 2026 | ||
| Multi-instance Point Cloud Registration | Scan2CAD (test) | 17 | Feb 26, 2026 | ||
| Multi-instance Point Cloud Registration | Scan2CAD single-frame | 17 | Feb 26, 2026 | ||
| Semantic Segmentation | Synthia to {Cityscapes (C), BDD (B), Mapillary (M)} | 17 | Feb 26, 2026 | ||
| Vision-and-Language Navigation | CVDN (val-unseen) | 17 | Jun 19, 2026 |