Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 105 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR10 | 114 | Apr 24, 2026 | ||
| Anomaly Segmentation | MVTec AD | 114 | Jun 29, 2026 | ||
| Summarization | PubMed (test) | 114 | May 13, 2026 | ||
| Referring Image Segmentation | RefCOCOg (val) | 114 | May 14, 2026 | ||
| Deblurring | RealBlur-J | 114 | Jul 2, 2026 | ||
| Cross-modality Person Re-identification | SYSU-MM01 (Indoor Search) | 114 | Feb 26, 2026 | ||
| Action Segmentation | 50Salads | 114 | Feb 26, 2026 | ||
| Handwritten text recognition | IAM (test) | 114 | Jul 9, 2026 | ||
| Monocular Depth Estimation | KITTI (test) | 114 | Apr 28, 2026 | ||
| Unsupervised Domain Adaptation | ImageCLEF DA | 114 | Apr 30, 2026 | ||
| Text-to-image Retrieval | CUHK-PEDES (test) | 114 | May 1, 2026 | ||
| Temporal Action Proposal | ActivityNet v1.3 (val) | 114 | Feb 27, 2026 | ||
| Semantic Segmentation | Cityscapes adaptation from Synthia 1.0 (val) | 114 | Feb 26, 2026 | ||
| Fine-grained Visual Categorization | Stanford Cars (test) | 114 | Mar 18, 2026 | ||
| Person Re-identification | Market-1501 single query | 114 | Feb 26, 2026 | ||
| 3D Object Part Segmentation | ShapeNet Part (test) | 114 | Feb 26, 2026 | ||
| Coreference Resolution | CoNLL English 2012 (test) | 114 | Feb 27, 2026 | ||
| Super-Resolution | Set5 x3 | 114 | May 19, 2026 | ||
| Molecule Captioning | ChEBI-20 (test) | 114 | Apr 7, 2026 | ||
| Speech Enhancement | VoiceBank + DEMAND (VB-DMD) (test) | 114 | Jun 23, 2026 | ||
| Mathematical Reasoning | AMC 23 | 113 | May 29, 2026 | ||
| Binary classification | TALENT (test) | 113 | Apr 14, 2026 | ||
| Question Answering | NQ | 113 | May 25, 2026 | ||
| Mathematical Reasoning | MATH 500 | 113 | Jun 26, 2026 | ||
| Correctness Prediction | TriviaQA | 113 | May 7, 2026 |