Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 798 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Face Normal Estimation | Photoface (test) | 32 | Feb 26, 2026 | ||
| Person Re-Identification | PRID (test) | 32 | Feb 26, 2026 | ||
| Image Reconstruction | DIV2K (val) | 32 | Apr 27, 2026 | ||
| Image-to-Image Translation | CelebA-HQ | 32 | May 19, 2026 | ||
| Extractive Summarization | PubMed (test) | 32 | Feb 26, 2026 | ||
| Image Demoireing | TIP 2018 (test) | 32 | Jul 8, 2026 | ||
| Deep Metric Learning | SOP (test) | 32 | Feb 26, 2026 | ||
| Low-light image enhancement | SID (test) | 32 | Mar 12, 2026 | ||
| Image Classification | CIFAR-100 Sym-50% (test) | 32 | Feb 26, 2026 | ||
| Nuclear Instance Segmentation | CoNSeP | 32 | Mar 10, 2026 | ||
| Open Information Extraction | OIE 2016 (test) | 32 | Feb 26, 2026 | ||
| Continual Learning | Permuted MNIST | 32 | May 18, 2026 | ||
| Point Cloud Completion | ShapeNet seen categories | 32 | Feb 26, 2026 | ||
| Emotion Detection | MELD (test) | 32 | Feb 26, 2026 | ||
| Named Entity Recognition | JNLPBA (test) | 32 | May 13, 2026 | ||
| Weakly supervised object localization | ImageNet | 32 | Feb 26, 2026 | ||
| Indoor Scene Segmentation | S3DIS (6-fold val) | 32 | Feb 26, 2026 | ||
| Object Part Segmentation | ShapeNet Parts 50 (test) | 32 | Jun 11, 2026 | ||
| Visual Question Answering | GQA (val) | 32 | Mar 19, 2026 | ||
| Silhouette prediction | Blobby dataset (test) | 32 | Feb 26, 2026 | ||
| Silhouette Prediction | Blobby | 32 | Feb 26, 2026 | ||
| Depth Estimation | KITTI improved ground truth 2015 (93% Eigen split) | 32 | Feb 26, 2026 | ||
| White-box Adversarial Robustness | MNIST (test) | 32 | Feb 26, 2026 | ||
| Fact Verification | FEVER (test) | 32 | Feb 26, 2026 | ||
| Early Action Recognition | EPIC-KITCHENS (val) | 32 | Feb 26, 2026 |