Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 386 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Super-Resolution | BSDS100 2x | 50 | Mar 13, 2026 | ||
| Generalized Few-Shot Learning | ImageNet All classes 2012 | 50 | Feb 26, 2026 | ||
| Logical Query Answering | FB15k (test) | 50 | Mar 18, 2026 | ||
| Scene Completion | NYU dataset (test) | 50 | Feb 26, 2026 | ||
| Person Re-identification | Market-1501 to MSMT17 | 50 | Feb 26, 2026 | ||
| Unsupervised Video Object Segmentation | DAVIS 2016 (test) | 50 | Feb 26, 2026 | ||
| Action Recognition | NTU RGB+D v1 (Cross-Subject (CS)) | 50 | Feb 26, 2026 | ||
| Lip-reading | LRW-1000 (test) | 50 | Feb 26, 2026 | ||
| Node Clustering | Cora (test) | 50 | Jun 23, 2026 | ||
| Semantic Segmentation | Nighttime Driving (test) | 50 | Mar 26, 2026 | ||
| Zero-shot Learning | SUN (unseen) | 50 | Feb 26, 2026 | ||
| Action Recognition | UCF101 1 (test) | 50 | Feb 26, 2026 | ||
| Semantic Segmentation | SYNTHIA-to-Cityscapes (SYN2CS) 16 classes (val) | 50 | Mar 10, 2026 | ||
| Deraining | Rain100H (test) | 50 | Feb 26, 2026 | ||
| Named Entity Recognition | Weibo (test) | 50 | Feb 26, 2026 | ||
| Predicate Classification | Visual Genome (test) | 50 | Feb 26, 2026 | ||
| Video Object Segmentation | YouTube-Objects | 50 | Feb 26, 2026 | ||
| Action Recognition | NTU RGB+D | 50 | Apr 21, 2026 | ||
| Object Detection | PASCAL VOC 2007 | 50 | Jun 18, 2026 | ||
| Open-Ended Visual Question Answering | VQA 1.0 (test-standard) | 50 | Feb 27, 2026 | ||
| Link Prediction | Citeseer (test) | 50 | May 28, 2026 | ||
| Image Modeling | CIFAR-10 (test) | 50 | Jun 15, 2026 | ||
| Protein-Ligand Binding Affinity Prediction | PDBbind Sequence Identity (60%) 2017 | 50 | Mar 19, 2026 | ||
| Out-of-distribution detection | ImageNet-1k vs NINCO | 50 | Apr 30, 2026 | ||
| Fine-grained Image Classification | FGVC-Aircraft | 50 | May 1, 2026 |