Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 299 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| End-to-end Open-Domain Question Answering | NQ (test) | 59 | May 8, 2026 | ||
| Video Prediction | BAIR (test) | 59 | Feb 26, 2026 | ||
| Image Classification | Office-Home | 59 | Feb 26, 2026 | ||
| Scene Text Recognition | CUTE (test) | 59 | Feb 26, 2026 | ||
| Image Generation | STL-10 (test) | 59 | Feb 26, 2026 | ||
| Named Entity Recognition | CoNLL NER 2002/2003 (test) | 59 | Feb 26, 2026 | ||
| Image Classification | Stanford Cars (val) | 59 | Mar 4, 2026 | ||
| Retinal vessel segmentation | CHASE DB1 | 59 | Jun 5, 2026 | ||
| Video-level classification | Kinetics 400 (test) | 59 | Feb 26, 2026 | ||
| Referring Image Segmentation | ReferIt (test) | 59 | Mar 20, 2026 | ||
| Scene Text Recognition | CUTE80 | 59 | Mar 20, 2026 | ||
| Multi-Object Tracking | MOT 2016 (test) | 59 | Feb 26, 2026 | ||
| Open-domain Question Answering | TriviaQA open (test) | 59 | May 11, 2026 | ||
| Aspect-level Sentiment Classification | SemEval Laptop 2014 (test) | 59 | Feb 27, 2026 | ||
| Molecular Property Classification | MoleculeNet BBBP | 59 | Apr 29, 2026 | ||
| Machine Translation | WMT De-En 14 (test) | 59 | Feb 26, 2026 | ||
| Relation Extraction | Wiki-KBP (test) | 59 | Feb 26, 2026 | ||
| Object Detection | PASCAL VOC 2007 (test) | 59 | Feb 26, 2026 | ||
| Clinical prediction | MIMIC-III | 59 | May 21, 2026 | ||
| Classification | MoleculeNet BBBP (test) | 59 | May 14, 2026 | ||
| Natural Language Understanding | GLUE (test val) | 59 | Feb 26, 2026 | ||
| Retrosynthesis | USPTO-50k Reaction type unknown (test) | 59 | Feb 26, 2026 | ||
| Image Classification | CINIC-10 | 59 | Apr 28, 2026 | ||
| Mathematical Reasoning | OlyBench | 59 | Mar 13, 2026 | ||
| Image Classification | WebVision 1.0 (val) | 59 | Feb 27, 2026 |