Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2077 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | Dyna.-Pla. (val) | 17 | Feb 26, 2026 | ||
| Gaze Following | ChildPlay | 17 | May 27, 2026 | ||
| Text Detection | SCUT-CTW1500 (test) | 17 | Feb 26, 2026 | ||
| Multimodal Classification | Hateful Memes | 17 | Feb 27, 2026 | ||
| Continual Learning | ImageNet 100 (test) | 17 | Feb 26, 2026 | ||
| Image Super-Resolution | F2K | 17 | Feb 26, 2026 | ||
| Object Erasure | CIFAR-10 Bird Erased | 17 | Feb 26, 2026 | ||
| Object Erasure | CIFAR-10 Airplane Erased | 17 | Feb 26, 2026 | ||
| Instruction Induction | Instruction Induction | 17 | Feb 26, 2026 | ||
| Correlation with human judgments | Flickr8K (Expert) | 17 | Feb 26, 2026 | ||
| Unconditional Image Generation | LSUN Church (test) | 17 | Feb 26, 2026 | ||
| Question Answering | WebSRC (test) | 17 | Feb 26, 2026 | ||
| Unconditional image generation | CelebA-HQ 256 x 256 | 17 | Feb 26, 2026 | ||
| Bias and Sentiment Evaluation | BOLD | 17 | Feb 26, 2026 | ||
| Multi-label image recognition with partial labels | Pascal VOC 2007 | 17 | Feb 26, 2026 | ||
| Regression | Skillcraft (test) | 17 | Feb 26, 2026 | ||
| Image Retrieval | ImageNet-4K 1.0 (test) | 17 | Feb 26, 2026 | ||
| Image Classification | ImageNet and ImageNet-V2 | 17 | Feb 26, 2026 | ||
| Image Classification | ImageNet Natural Distribution Shifts R, Sketch, A | 17 | Feb 26, 2026 | ||
| Semantic Segmentation | A2D2 (val) | 17 | Feb 26, 2026 | ||
| Class Incremental Learning | OmniBenchmark | 17 | Feb 26, 2026 | ||
| Speech Emotion Recognition | SUBESCO Bengali (Bn) | 17 | Feb 26, 2026 | ||
| Graph Classification | CMNIST color | 17 | Feb 26, 2026 | ||
| Depth Estimation | HyperSim (test) | 17 | Apr 21, 2026 | ||
| Point Cloud Classification | ModelNet40 (test) | 17 | Feb 27, 2026 |