Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1975 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Edge Detection | MDBD (test) | 18 | Feb 26, 2026 | ||
| Table Detection | ICDAR 2013 (test) | 18 | Feb 26, 2026 | ||
| Saliency prediction | MIT1003 (test) | 18 | Feb 26, 2026 | ||
| Language Modeling | BookCorpus (test) | 18 | Jul 9, 2026 | ||
| Facial Expression Recognition | MMI | 18 | Feb 26, 2026 | ||
| Named Entity Recognition | OntoNotes 4.0 | 18 | Feb 26, 2026 | ||
| Image Classification | ImageNet 10% labels 1K (val) | 18 | Feb 26, 2026 | ||
| Multiple-choice Question Answering | CommonsenseQA (dev) | 18 | Feb 26, 2026 | ||
| Image Denoising | DND Raw | 18 | Feb 26, 2026 | ||
| Node Classification | DISEASE δ = 0 (test) | 18 | Feb 26, 2026 | ||
| 6D Pose Estimation | LINEMOD 5 (test) | 18 | Feb 26, 2026 | ||
| Action Alignment | Breakfast | 18 | Feb 26, 2026 | ||
| Deep Clustering | Fashion-MNIST | 18 | Feb 26, 2026 | ||
| Deep Clustering | MNIST (test) | 18 | Feb 26, 2026 | ||
| Deep Clustering | MNIST full | 18 | Feb 26, 2026 | ||
| Summarization | CNN/Daily Mail full length (test) | 18 | Feb 26, 2026 | ||
| Presentation Attack Detection | WMCA grandtest protocol (dev) | 18 | Feb 26, 2026 | ||
| Fact Extraction and Verification | FEVER (test) | 18 | Feb 26, 2026 | ||
| Spoken Language Understanding | ATIS (test) | 18 | Feb 26, 2026 | ||
| Text Summarization | NYT (test) | 18 | Feb 26, 2026 | ||
| 20-way Few-Shot Image Classification | Omniglot (test) | 18 | Feb 27, 2026 | ||
| Clinical concept extraction | i2b2 2010 (test) | 18 | Mar 10, 2026 | ||
| Semantic Segmentation | Potsdam 3 (test) | 18 | Feb 26, 2026 | ||
| Duplicate Scene Video Retrieval | FIVR-5K | 18 | Feb 26, 2026 | ||
| Ad-hoc Document Ranking | WebTrack 2012-14 | 18 | Feb 26, 2026 |