Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 305 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Classification | German | 58 | May 20, 2026 | ||
| Action Classification | Smarthome (cross-subject) | 58 | Feb 26, 2026 | ||
| Named Entity Recognition | ACE 2005 (test) | 58 | Feb 26, 2026 | ||
| Instance Segmentation | LVIS 0.5 (val) | 58 | Feb 26, 2026 | ||
| Instance Segmentation | ScanNetV2 (val) | 58 | Feb 27, 2026 | ||
| Salient Object Detection | FBMS (test) | 58 | Feb 26, 2026 | ||
| Machine Translation | WMT 2016 (test) | 58 | Feb 27, 2026 | ||
| Place Recognition | Oxford RobotCar | 58 | Mar 4, 2026 | ||
| Semantic Segmentation | Dark Zurich (test) | 58 | Feb 26, 2026 | ||
| Abstractive Summarization | Gigaword (test) | 58 | Feb 26, 2026 | ||
| Node-level classification | Flickr | 58 | Feb 26, 2026 | ||
| Person Re-identification | Partial-REID | 58 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M v1 (test) | 58 | Feb 26, 2026 | ||
| Image Retrieval | Fashion200k (test) | 58 | Apr 2, 2026 | ||
| Trajectory Prediction | ZARA1 v1.0 (test) | 58 | Feb 26, 2026 | ||
| Digit Classification | USPS → MNIST target (test) | 58 | Feb 27, 2026 | ||
| Machine Translation | WMT16 English-German (test) | 58 | Feb 27, 2026 | ||
| Visual Dialog | VisDial v0.9 (test) | 58 | Feb 26, 2026 | ||
| Image Classification | ImageNet (test val) | 58 | Feb 26, 2026 | ||
| Action Classification | HMDB51 (split1) | 58 | Feb 26, 2026 | ||
| Image Classification | ImageNet ILSVRC 2012 (val) | 58 | Feb 26, 2026 | ||
| Image Classification | MNIST (val) | 58 | May 20, 2026 | ||
| Image Classification | ImageNet 1k (train) | 58 | Jun 2, 2026 | ||
| Maximum Independent Set | ER [700-800] | 58 | Jun 1, 2026 | ||
| Speech Separation | WHAM! (test) | 58 | Feb 26, 2026 |