Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2091 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Binary Classification | Binary CIFAR10 imb. 100 (test) | 17 | Feb 26, 2026 | ||
| Visual Question Answering | OCR-VQA (val) | 17 | Feb 27, 2026 | ||
| Image Classification | miniDomainNet | 17 | Feb 26, 2026 | ||
| Semantic Segmentation | NYUD | 17 | Feb 27, 2026 | ||
| Image Classification | CIFAR-100 | 17 | Feb 26, 2026 | ||
| Open-Domain Question Answering | WebQuestions (WebQ) (dev) | 17 | Feb 26, 2026 | ||
| Coreference Resolution | CoNLL 2012 | 17 | Feb 27, 2026 | ||
| Video Super-Resolution | VideoLQ (test) | 17 | Feb 26, 2026 | ||
| Anomaly Segmentation | Road Anomaly (val) | 17 | Mar 5, 2026 | ||
| Image Harmonization | DIH99 (test) | 17 | Feb 26, 2026 | ||
| Object Detection | Object365 | 17 | Feb 27, 2026 | ||
| Classification | CUB (test) | 17 | Feb 26, 2026 | ||
| Widget Captioning | Widget Captioning (test) | 17 | Feb 26, 2026 | ||
| Mixture Proportion Estimation | Binarized CIFAR | 17 | Feb 26, 2026 | ||
| ICU Treatment Recommendation | MIMIC-III v1.4 (test) | 17 | Feb 26, 2026 | ||
| Image Generation | ImageNet (train val) | 17 | Feb 26, 2026 | ||
| Image classification | BFFHQ bias-conflicting (test) | 17 | Mar 23, 2026 | ||
| CATE estimation | IHDP Setup D (out-of-sample) | 17 | Feb 26, 2026 | ||
| CATE estimation | IHDP Setup D (in-sample) | 17 | Feb 26, 2026 | ||
| CATE estimation | IHDP Setup C (out-of-sample) | 17 | Feb 26, 2026 | ||
| CATE estimation | IHDP Setup C (in-sample) | 17 | Feb 26, 2026 | ||
| Node classification | pokec 50/25/25 (test) | 17 | Feb 26, 2026 | ||
| Image Denoising | CBSD68 Gaussian noise, σ = 25 (test) | 17 | Feb 26, 2026 | ||
| Node Classification | Squirrel (dense) | 17 | Jun 25, 2026 | ||
| Natural Language Generation | WebNLG unseen categories | 17 | Feb 26, 2026 |