Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2099 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Ad-hoc Retrieval | ClueWeb-09-Cat-B Topic titles (test) | 17 | Feb 26, 2026 | ||
| 3D Reconstruction | ShapeNet | 17 | Feb 26, 2026 | ||
| Classification | Omniglot 20-way (test) | 17 | Feb 26, 2026 | ||
| NIR-VIS face recognition | Oulu-CASIA NIR-VIS Database (test) | 17 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | HumanEva-I Jogging | 17 | Feb 26, 2026 | ||
| Person Search | CUHK-SYSU 100 gallery size | 17 | Feb 26, 2026 | ||
| Action Segmentation | 50 Salads Mid | 17 | Apr 24, 2026 | ||
| Sentiment Classification | SemEval Twitter Sentiment Analysis 2016 (test) | 17 | Feb 26, 2026 | ||
| Sentiment Classification | SemEval Twitter Sentiment Analysis 2015 (test) | 17 | Feb 26, 2026 | ||
| Sentiment Classification | SemEval Twitter Sentiment Analysis 2014 (test) | 17 | Feb 26, 2026 | ||
| Sentiment Classification | SemEval Twitter Sentiment Analysis 2013 (test) | 17 | Feb 26, 2026 | ||
| Image Quality Assessment | LIVE (full) | 17 | Feb 26, 2026 | ||
| Image Quality Assessment | TID 2008 (full) | 17 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | KTH Multiview Football II (Sequence 1 of Player 2) | 17 | Feb 26, 2026 | ||
| Human Attribute Prediction | WIDER-Attribute (test) | 17 | Feb 26, 2026 | ||
| Image Search | COCO | 17 | Feb 26, 2026 | ||
| Visual Question Answering (Multiple-Choice) | VQA (test-dev) | 17 | Feb 26, 2026 | ||
| Document-level sentiment classification | Yelp 13 | 17 | Feb 26, 2026 | ||
| Age Estimation | FG-NET (LOPO) | 17 | Feb 26, 2026 | ||
| Image Denoising | 68-image dataset sigma=50 (test) | 17 | Feb 26, 2026 | ||
| Visual Question Answering (Multiple-Choice) | VQA (test-standard) | 17 | Feb 26, 2026 | ||
| Action Recognition | UT-Kinect (leave-one-out-cross-validation protocol) | 17 | Feb 26, 2026 | ||
| Sentiment Classification | Amazon Polarity (test) | 17 | Feb 26, 2026 | ||
| Action Recognition | 3D Action Pairs | 17 | Feb 26, 2026 | ||
| Image Captioning | Flickr 8k | 17 | Feb 26, 2026 |