Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1415 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Detection | UOBD v1 (test) | 22 | Apr 23, 2026 | ||
| Object Detection | MS-COCO 2017 (test-dev) | 22 | Mar 31, 2026 | ||
| Dialogue Relation Extraction | DialogRE (dev) | 22 | Feb 26, 2026 | ||
| Instance Segmentation | ScanNet v2 (test) | 22 | Feb 26, 2026 | ||
| Semantic Type Classification | VizNet (test) | 22 | Feb 26, 2026 | ||
| Video Interpolation | HQF DAVIS240 3 frames skips (all sequences) | 22 | Feb 26, 2026 | ||
| Retrosynthesis prediction | USPTO-50k | 22 | Feb 26, 2026 | ||
| Facial Landmark Detection | COFW (Full) | 22 | Feb 26, 2026 | ||
| Extractive Question Answering | HotpotQA MRQA | 22 | Feb 27, 2026 | ||
| Extractive Question Answering | SearchQA MRQA | 22 | Feb 27, 2026 | ||
| Extractive Question Answering | NewsQA MRQA | 22 | Feb 27, 2026 | ||
| Extractive Question Answering | Natural Questions MRQA | 22 | Feb 27, 2026 | ||
| Extractive Question Answering | TriviaQA MRQA | 22 | Feb 27, 2026 | ||
| Machine Translation | IWSLT14 DE-EN | 22 | Feb 26, 2026 | ||
| Machine Translation | WMT19 Zh-En (test) | 22 | Feb 26, 2026 | ||
| Detoxification | RealToxicityPrompts | 22 | Feb 26, 2026 | ||
| Opinion Summarization | Amazon (test) | 22 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | Average (iNaturalist, SUN, Places, Textures) (test) | 22 | Feb 26, 2026 | ||
| Face Parsing | Helen (test) | 22 | Feb 26, 2026 | ||
| Semantic Segmentation | RETOUCH Spectralis (test) | 22 | Feb 26, 2026 | ||
| Image Classification | WebVision mini 1.0 (val) | 22 | Feb 26, 2026 | ||
| Lossless Image Compression | CLIC.m (val) | 22 | Feb 26, 2026 | ||
| Lossless Image Compression | CLIC.p (val) | 22 | Feb 26, 2026 | ||
| Lossless Image Compression | DIV2K (val) | 22 | Feb 26, 2026 | ||
| Geometric Matching | MegaDepth (test) | 22 | Feb 26, 2026 |