Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1518 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | WebVision-1000 (val) | 21 | Feb 26, 2026 | ||
| Table Fact Verification | TABFACT (val) | 21 | Feb 26, 2026 | ||
| End-to-end Open-Domain Question Answering | TREC (test) | 21 | Feb 26, 2026 | ||
| Video Question Answering | How2QA (test) | 21 | Feb 27, 2026 | ||
| Action Detection | JHMDB-21 | 21 | Feb 26, 2026 | ||
| Image Classification | Stanford Dogs (test) | 21 | Feb 26, 2026 | ||
| RGB Saliency Detection | SIP (test) | 21 | Feb 26, 2026 | ||
| RGB saliency detection | HKU-IS | 21 | Feb 26, 2026 | ||
| Document Layout Analysis | PubLayNet (val) | 21 | Feb 26, 2026 | ||
| Visual SLAM | TUM RGB-D fr2 xyz | 21 | Feb 26, 2026 | ||
| Vehicle Re-identification | VERI-Wild Large | 21 | Feb 26, 2026 | ||
| Vehicle Re-identification | VERI-Wild (Medium) | 21 | Feb 26, 2026 | ||
| Partial Person Re-identification | PartialREID | 21 | Feb 26, 2026 | ||
| Super-Resolution | RealSR Nikon (test) | 21 | Feb 26, 2026 | ||
| Super-Resolution | RealSR Canon (test) | 21 | Feb 26, 2026 | ||
| Node Classification | Cornell full-supervised | 21 | Feb 26, 2026 | ||
| Temporal Activity Localization | ActivityNet 1.3 (test) | 21 | Feb 26, 2026 | ||
| Grayscale Image Denoising | Kodak24 (test) | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 20 (val) | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (val) | 21 | Feb 26, 2026 | ||
| Human-Object Interaction Detection | HICO-DET 9 (test) | 21 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M 13 (test) | 21 | Feb 26, 2026 | ||
| Link Prediction | YAGO3-10 filtered (test) | 21 | Feb 26, 2026 | ||
| Named Entity Recognition | German GermEval14 (test) | 21 | Jun 2, 2026 | ||
| Commonsense Reasoning | HELLASWAG (test) | 21 | Feb 26, 2026 |