Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 695 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Question Answering | TVQA (test) | 35 | Mar 25, 2026 | ||
| Video Super-Resolution | Vimeo-90k Fast | 35 | Feb 26, 2026 | ||
| Image Classification | iNaturalist 2017 (val) | 35 | Feb 26, 2026 | ||
| Joint Entity and Relation Extraction | CONLL04 | 35 | Jun 4, 2026 | ||
| Semantic keypoint transfer | PF-Pascal (test) | 35 | Feb 26, 2026 | ||
| Image Classification | CIFAR to STL standard (test) | 35 | Feb 26, 2026 | ||
| Image Retrieval | R-Oxford Medium | 35 | Feb 26, 2026 | ||
| Multi-view Stereo Reconstruction | DTU (evaluation) | 35 | Feb 26, 2026 | ||
| Named Entity Recognition | CoNLL (test) | 35 | Jun 18, 2026 | ||
| Text Classification | movie review dataset (test) | 35 | Mar 5, 2026 | ||
| Image Retrieval | INSTRE | 35 | Apr 16, 2026 | ||
| Machine Translation | IWSLT De-En 14 | 35 | May 7, 2026 | ||
| Crowd Counting | Mall dataset (test) | 35 | Mar 26, 2026 | ||
| Video Object Segmentation | YoutubeObjects (val) | 35 | Feb 26, 2026 | ||
| Shadow Detection | UCF (test) | 35 | May 13, 2026 | ||
| Multi-object tracking | MOTChallenge 2015 (test) | 35 | Feb 26, 2026 | ||
| Text-to-Image Synthesis | MS-COCO (val) | 35 | Feb 26, 2026 | ||
| Language Modeling | Yelp (test) | 35 | Feb 26, 2026 | ||
| Single Image Dehazing | Synthetic Images SRE | 35 | Feb 26, 2026 | ||
| Single Image Dehazing | Synthetic Images ARE | 35 | Feb 26, 2026 | ||
| Single Image Dehazing | Synthetic Images CRE | 35 | Feb 26, 2026 | ||
| Object Detection | KITTI (test) | 35 | Feb 26, 2026 | ||
| Phrase Localization | Flickr30K Entities (test) | 35 | Feb 26, 2026 | ||
| Temporal Action Localization | THUMOS 2014 (test) | 35 | Feb 27, 2026 | ||
| Super-Resolution | Set14 x4 | 35 | Mar 9, 2026 |