Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 333 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Unconditional Layout Generation | Rico | 55 | Feb 26, 2026 | ||
| 3D Reconstruction | DTU | 55 | May 27, 2026 | ||
| Video Anomaly Detection | UBnormal (test) | 55 | Jul 2, 2026 | ||
| Relation Extraction | SemEval (test) | 55 | Jun 23, 2026 | ||
| Homography estimation | HPatches | 55 | Apr 14, 2026 | ||
| Hyper-relational extraction | HyperRED (test) | 55 | Feb 26, 2026 | ||
| 3D Keypoint Detection | Redwood | 55 | Feb 26, 2026 | ||
| Few-shot segmentation | COCO 20^i (val) | 55 | Feb 26, 2026 | ||
| 3D Object Detection | STF heavy snowfall (test) | 55 | Feb 26, 2026 | ||
| Super-Resolution | Manga109 x3 | 55 | May 19, 2026 | ||
| Text-to-Video Retrieval | MSR-VTT (9K) | 55 | Feb 26, 2026 | ||
| 3D Question Answering | ScanQA w/ objects (test) | 55 | Feb 26, 2026 | ||
| Person Re-identification | Average (CUHK03-NP, Market-1501, MSMT17) | 55 | Feb 26, 2026 | ||
| 3D Visual Grounding | ScanRefer Overall | 55 | Jun 9, 2026 | ||
| Open-domain Question Answering | WebQuestions (WebQ) (test) | 55 | Feb 26, 2026 | ||
| Speech-to-speech translation | Fisher Spanish-English (test) | 55 | Feb 26, 2026 | ||
| Anomaly Detection | Avenue | 55 | Feb 26, 2026 | ||
| Speech Enhancement | VoiceBank-DEMAND | 55 | Jun 19, 2026 | ||
| Semantic Entity Recognition | CORD | 55 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 | 55 | Feb 26, 2026 | ||
| Video Deblurring | GOPRO (test) | 55 | Feb 26, 2026 | ||
| Image Captioning | Flickr30k | 55 | Feb 26, 2026 | ||
| Image Captioning | COCO Caption | 55 | Feb 26, 2026 | ||
| Image Denoising | BSD68 sigma=25 | 55 | May 19, 2026 | ||
| Video Retrieval | UCF101 (test) | 55 | Feb 26, 2026 |