Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1038 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Context-dependent Text-to-SQL | SParC 1.0 (dev) | 27 | Feb 26, 2026 | ||
| Place Recognition | Oxford Robotcar (test) | 27 | Feb 26, 2026 | ||
| Depth Completion | KITTI-Depth | 27 | Feb 26, 2026 | ||
| Action Anticipation | EPIC-KITCHENS seen S1 (test) | 27 | Feb 26, 2026 | ||
| Text Simplification | WikiLarge (test) | 27 | Feb 26, 2026 | ||
| 3D Semantic Segmentation | S3DIS | 27 | Apr 14, 2026 | ||
| Response Generation | MultiWOZ (test) | 27 | Feb 26, 2026 | ||
| Pronoun Disambiguation | Winograd Schema Challenge | 27 | Feb 26, 2026 | ||
| Classification | PASCAL VOC | 27 | Feb 26, 2026 | ||
| Natural Language Understanding | Snips (test) | 27 | Feb 26, 2026 | ||
| Vision-and-Language Navigation | Room-to-Room (R2R) (val unseen) | 27 | Mar 9, 2026 | ||
| Sleep Stage Classification | Sleep-EDF | 27 | Apr 7, 2026 | ||
| 3D Multi-person Pose Estimation | Shelf (test) | 27 | Feb 26, 2026 | ||
| Automatic Speech Recognition | NIST CTS CallHome 2000 | 27 | Feb 26, 2026 | ||
| Entity Linking | KORE50 | 27 | Feb 26, 2026 | ||
| Machine Translation | NIST MT 06 2006 (test) | 27 | Feb 26, 2026 | ||
| Machine Translation | NIST MT 04 2004 (test) | 27 | Feb 26, 2026 | ||
| Image Modeling | OMNIGLOT (test) | 27 | Feb 26, 2026 | ||
| Link Prediction | NELL-995 (test) | 27 | Feb 26, 2026 | ||
| Image Captioning | COCO (test) | 27 | Feb 26, 2026 | ||
| Constituency Parsing | WSJ Penn Treebank (test) | 27 | Feb 26, 2026 | ||
| CS reconstruction | Set14 (test) | 27 | Feb 26, 2026 | ||
| CS reconstruction | Set5 (test) | 27 | Feb 26, 2026 | ||
| Machine Translation | WMT de-en | 27 | Mar 11, 2026 | ||
| Pedestrian Attribute Recognition | RAP v2 | 27 | Feb 26, 2026 |