Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 797 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Denoising | SIDD raw-RGB (val) | 32 | Mar 10, 2026 | ||
| Word Sense Disambiguation | WiC (dev) | 32 | Feb 26, 2026 | ||
| Image Classification | ImageNet (10%) | 32 | Feb 26, 2026 | ||
| Image Classification | CIFAR FS | 32 | Jun 12, 2026 | ||
| Pain Intensity Estimation | Older Adult Control | 32 | Feb 26, 2026 | ||
| Pain Intensity Estimation | Dementia | 32 | Feb 26, 2026 | ||
| Question Answering | TriviaQA (dev) | 32 | Feb 26, 2026 | ||
| Nested Named Entity Recognition | ACE 2004 | 32 | Feb 26, 2026 | ||
| Depth Prediction | Sintel | 32 | Feb 26, 2026 | ||
| Video Panoptic Segmentation | Cityscapes-VPS (test) | 32 | Feb 26, 2026 | ||
| Generalized Few-Shot Learning | Two-Level SUN distributions (test) | 32 | Feb 26, 2026 | ||
| Image Classification | S-CIFAR-10 Class-IL | 32 | Feb 26, 2026 | ||
| Text Retrieval | Flickr30k Karpathy (test) | 32 | Apr 15, 2026 | ||
| Out-of-distribution Detection | ImageNet-30 In-distribution labeled (test) | 32 | Feb 26, 2026 | ||
| Multi-view 3D object reconstruction | Things3D | 32 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | HumanEva | 32 | Feb 26, 2026 | ||
| Action Step Localization | CrossTask (test) | 32 | Feb 27, 2026 | ||
| Clustering | Imagenet-dog-15 (test) | 32 | Feb 26, 2026 | ||
| Video Summarization | TVSum (5-fold cross-val) | 32 | Mar 4, 2026 | ||
| Classification | Waveform 21,1647,3353 | 32 | Feb 26, 2026 | ||
| Face Super-Resolution | CelebA (test) | 32 | Feb 26, 2026 | ||
| Attributional Robustness | CIFAR-10 (test) | 32 | Jun 5, 2026 | ||
| Pedestrian Trajectory Prediction | ZARA1 UCY scene ETH/UCY (test) | 32 | Feb 26, 2026 | ||
| Object Detection | UAVDT | 32 | Jun 30, 2026 | ||
| Image Classification | tieredImageNet (test) | 32 | Feb 26, 2026 |