Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1970 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Classification | Protein (test) | 18 | May 11, 2026 | ||
| Classification | australian | 18 | Mar 11, 2026 | ||
| Classification | kc1 | 18 | Feb 26, 2026 | ||
| Image Classification | TinyImageNet et = 1/255 (val) | 18 | Feb 26, 2026 | ||
| Conditional estimation | Dynamic MNIST (test) | 18 | Feb 26, 2026 | ||
| Vital signs prediction | BDIMC healthcare datasets | 18 | Feb 26, 2026 | ||
| Few-shot Image Classification | CIFAR-FS (test) | 18 | Feb 26, 2026 | ||
| Time series imputation | air quality | 18 | Jun 5, 2026 | ||
| Object Detection | MSCOCO 2017 (minival) | 18 | Feb 26, 2026 | ||
| Group-level video emotion classification | VGAF (val) | 18 | Jun 9, 2026 | ||
| Entity Relation Extraction | FUNSD (test) | 18 | Feb 26, 2026 | ||
| Low-shot image classification | VOC 2007 (test) | 18 | Feb 27, 2026 | ||
| Multi-label recognition | MS-COCO (val) | 18 | Feb 26, 2026 | ||
| Information Extraction | CORD | 18 | Feb 26, 2026 | ||
| Video Quality Assessment | LIVE Livestream | 18 | Feb 26, 2026 | ||
| Classification | bank-marketing | 18 | May 12, 2026 | ||
| Camera Pose Regression | Oxford RobotCar (Full) | 18 | Feb 26, 2026 | ||
| Open Information Extraction | PENN | 18 | Feb 27, 2026 | ||
| Open Information Extraction | NYT | 18 | Feb 27, 2026 | ||
| Open Information Extraction | WEB | 18 | Feb 27, 2026 | ||
| Open Information Extraction | OIE 2016 | 18 | Feb 27, 2026 | ||
| Interactive Instance Segmentation | COCO (MVal) | 18 | Apr 15, 2026 | ||
| Dialogue Response Selection | Ubuntu (test) | 18 | Feb 26, 2026 | ||
| Text Style Transfer | IMDB (test) | 18 | Feb 26, 2026 | ||
| Text Style Transfer | Yelp (test) | 18 | Feb 26, 2026 |