Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 268 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Captioning | NoCaps (test) | 63 | Jun 26, 2026 | ||
| Video retrieval | UCF101 | 63 | Feb 27, 2026 | ||
| Line Segment Detection | YorkUrban (test) | 63 | Mar 13, 2026 | ||
| Image Classification | PACS (out-of-domain) | 63 | Feb 26, 2026 | ||
| Human motion prediction | HumanEva-I (test) | 63 | Mar 24, 2026 | ||
| Defocus Deblurring | DP Dataset Combined 1.0 (test) | 63 | Feb 26, 2026 | ||
| Named Entity Recognition | MSRA (test) | 63 | Feb 26, 2026 | ||
| 5-way Few-shot Image Classification | CIFAR-FS (test) | 63 | Jun 24, 2026 | ||
| Relation Extraction | SemEval | 63 | Feb 26, 2026 | ||
| Visual Commonsense Reasoning | VCR (val) | 63 | Feb 26, 2026 | ||
| Object Tracking | OTB 2015 (test) | 63 | Feb 26, 2026 | ||
| Answer Sentence Selection | TREC-QA (test) | 63 | Feb 27, 2026 | ||
| Named Entity Recognition | WNUT 2017 (test) | 63 | Feb 26, 2026 | ||
| Reading Comprehension | DROP (dev) | 63 | Feb 27, 2026 | ||
| Visual Object Tracking | OTB 2015 | 63 | Mar 4, 2026 | ||
| Scene Text Recognition | IC03 (test) | 63 | Feb 26, 2026 | ||
| Normal Estimation | PCPNet (test) | 63 | Feb 26, 2026 | ||
| Vehicle Re-identification | VehicleID 2400 (test) | 63 | Feb 26, 2026 | ||
| Image Classification | NABirds | 63 | May 18, 2026 | ||
| Image Retrieval | Paris Revisited (Medium) | 63 | Feb 26, 2026 | ||
| Crowd Counting | UCF_CC_50 | 63 | Jun 2, 2026 | ||
| Scene Graph Classification | Visual Genome (test) | 63 | Feb 26, 2026 | ||
| Image Deblurring | Köhler Dataset | 63 | Apr 23, 2026 | ||
| Image Classification | USPS -> MNIST (test) | 63 | Feb 26, 2026 | ||
| Person Re-identification | CUHK01 | 63 | Apr 2, 2026 |