Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 133 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Commonsense Reasoning | Commonsense Reasoning Suite BoolQ, PIQA, HellaS, WinoG, ARC-e, ARC-c, OBQA | 98 | Jun 23, 2026 | ||
| Image Watermarking | ImageNet | 98 | Apr 14, 2026 | ||
| Exemplar-Free Class-Incremental Learning | TinyImageNet | 98 | Jun 26, 2026 | ||
| Node Classification | Roman-empire (test) | 98 | Jun 4, 2026 | ||
| Low-Light Image Enhancement | LOL real v2 | 98 | Jul 7, 2026 | ||
| Object Detection | ODinW-13 | 98 | Feb 26, 2026 | ||
| Face Verification | CA-LFW | 98 | Apr 13, 2026 | ||
| Medical Image Segmentation | LA | 98 | Jul 3, 2026 | ||
| Graph classification | Peptides-func (test) | 98 | Jun 26, 2026 | ||
| Automatic Speech Recognition | LibriSpeech 960h (test-other) | 98 | Jun 11, 2026 | ||
| 5-way Few-shot Classification | Cars | 98 | Jun 5, 2026 | ||
| Scene Text Recognition | CUTE 288 samples (test) | 98 | Feb 26, 2026 | ||
| Selective Classification | CIFAR-10 (test) | 98 | Apr 28, 2026 | ||
| Few-shot Classification | miniImageNet | 98 | May 15, 2026 | ||
| Dialogue State Tracking | MultiWOZ 2.2 (test) | 98 | May 7, 2026 | ||
| Text Classification | R52 | 98 | Jul 8, 2026 | ||
| Category-level Retrieval | iNaturalist 2018 | 98 | Feb 26, 2026 | ||
| Image Classification | ImageNet Matched Frequency V2 | 98 | May 8, 2026 | ||
| Relation Extraction | DocRED (dev) | 98 | Feb 26, 2026 | ||
| Semantic Segmentation | GTA5 to Cityscapes 1.0 (val) | 98 | Feb 26, 2026 | ||
| Image Classification | ImageNet (10% labels) | 98 | Feb 27, 2026 | ||
| Image Denoising | SIDD 1 (test) | 98 | May 5, 2026 | ||
| Video Captioning | YouCook II (val) | 98 | Feb 27, 2026 | ||
| Visual Dialog | VisDial v1.0 (test-std) | 98 | May 26, 2026 | ||
| Action Recognition | Kinetics | 98 | Mar 19, 2026 |