Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 917 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Pansharpening | GeoEye-1 PairMax (London+Trenton) | 29 | Feb 26, 2026 | ||
| Dialogue State Tracking | MultiWOZ 2.0 (test) | 29 | Mar 11, 2026 | ||
| Multi-modal dialogue retrieval | PhotoChat (test) | 29 | Feb 26, 2026 | ||
| Semantic Parsing | GeoQuery compositional | 29 | Feb 27, 2026 | ||
| Medical Image Segmentation | MosMedData+ (test) | 29 | Feb 26, 2026 | ||
| Sentiment Analysis | Yelp (test) | 29 | Feb 26, 2026 | ||
| No-Reference Image Quality Assessment | CSIQ-IQA | 29 | Jun 30, 2026 | ||
| Semantic Segmentation | DigestPath (test) | 29 | Feb 26, 2026 | ||
| Detoxification | Jigsaw (test) | 29 | Feb 26, 2026 | ||
| Object Classification | ScanObjectNN OBJ_ONLY v1.0 | 29 | Feb 26, 2026 | ||
| Object Classification | ScanObjectNN OBJ_BG v1.0 | 29 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (full) | 29 | May 7, 2026 | ||
| Group Dance Generation | AIOZ-GDANCE 1.0 (test) | 29 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1k 1 (val) | 29 | Jun 2, 2026 | ||
| 3D Object Detection | Waymo Open Dataset 0.2 labeled (val) | 29 | Feb 26, 2026 | ||
| Hand Reconstruction | InterHand 2.6M (test) | 29 | Apr 15, 2026 | ||
| Semantic Segmentation | Pascal VOC 5-3 protocol 2012 (val) | 29 | Feb 26, 2026 | ||
| Raw Image Reconstruction | NUS dataset Sony SLT-A57 | 29 | Feb 26, 2026 | ||
| Raw Image Reconstruction | NUS dataset Olympus E-PL6 | 29 | Feb 26, 2026 | ||
| Raw Image Reconstruction | NUS Samsung NX2000 | 29 | Feb 26, 2026 | ||
| Semantic Segmentation | Cityscapes (val) | 29 | Feb 26, 2026 | ||
| Point Cloud Completion | ShapeNet-ViPC (known categories) | 29 | Jul 7, 2026 | ||
| Control | DMControl | 29 | Feb 26, 2026 | ||
| Object Detection | MS-COCO (minival) | 29 | Mar 17, 2026 | ||
| Code Generation | APPS | 29 | May 15, 2026 |