Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1654 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | HotpotQA | 20 | Feb 26, 2026 | ||
| Backdoor mitigation | Lingspam | 20 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | Far OOD datasets (Dfar) (test) | 20 | Feb 26, 2026 | ||
| OOD Detection | ImageNet-1K Dnear | 20 | Feb 26, 2026 | ||
| Machine Translation | WMT De-En 23 | 20 | Feb 26, 2026 | ||
| Code Generation | HumanEval-X | 20 | Feb 26, 2026 | ||
| Commonsense Reasoning | Common Sense QA (test) | 20 | Feb 26, 2026 | ||
| Visual Perception Evaluation | MME Perception | 20 | Feb 26, 2026 | ||
| Gaussian Image Denoising | McMaster 2011 (test) | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | OCW-Math | 20 | Feb 26, 2026 | ||
| Mass Localization | VinDr held-out (test) | 20 | Feb 26, 2026 | ||
| Calcification Localization | VinDr held-out (test) | 20 | Feb 26, 2026 | ||
| Few-view 3D Reconstruction | RealEstate10K (test) | 20 | Feb 26, 2026 | ||
| Text-to-motion retrieval | KIT-ML (test) | 20 | Mar 26, 2026 | ||
| Text-to-Music Generation | MusicCaps (evaluation set) | 20 | Feb 26, 2026 | ||
| Image Watermarking | Stable Diffusion V2.1 | 20 | Feb 26, 2026 | ||
| Monocular 2D Object Detection | KITTI (test) | 20 | Feb 27, 2026 | ||
| Compositional Evaluation | SugarCrepe (test) | 20 | Mar 4, 2026 | ||
| Object Detection | FAIR1M 1.0 | 20 | Feb 26, 2026 | ||
| Single-image defocus deblurring | DPDD Outdoor Scenes (test) | 20 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 rho=100 long-tailed (test) | 20 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 | 20 | Feb 26, 2026 | ||
| Satellite Image Classification | EuroSAT | 20 | Apr 14, 2026 | ||
| Zero-shot Classification | Food 101 | 20 | May 20, 2026 | ||
| JPEG Artifact Removal | LIVE-1 (test) | 20 | Feb 26, 2026 |