Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1149 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OOD detection | CIFAR-10 standard (test) | 25 | Feb 26, 2026 | ||
| Video Person Re-identification | iLIDS-VID (test) | 25 | Feb 26, 2026 | ||
| Video Retrieval | ActivityNet | 25 | Feb 26, 2026 | ||
| Lossless Image Compression | Kodak (test) | 25 | Mar 31, 2026 | ||
| Scene Text Detection | MLT 2017 (test) | 25 | Feb 26, 2026 | ||
| Video Super-Resolution | Vid4 BD degradation 21 (test) | 25 | Feb 26, 2026 | ||
| Domain Adaptation | Office 3-shots 31 | 25 | Feb 26, 2026 | ||
| Named Entity Disambiguation | AIDA (test) | 25 | Feb 27, 2026 | ||
| Object Detection | VOC Novel Set 2 | 25 | Feb 27, 2026 | ||
| Time-series emotion perception | SEND v1 (test) | 25 | Feb 26, 2026 | ||
| Time-series emotion perception | SEND v1 (val) | 25 | Feb 26, 2026 | ||
| Continual Semantic Segmentation | ADE20k 50-50 (3 tasks) (val) | 25 | Feb 26, 2026 | ||
| Aspect Sentiment Triplet Extraction | 16Rest ASTE-Data-V1 (test) | 25 | Feb 26, 2026 | ||
| Clustering | E-MNIST | 25 | Feb 26, 2026 | ||
| Sentence Retrieval | MS-COCO 1K (test) | 25 | Feb 26, 2026 | ||
| Pansharpening | GaoFen2 (test) | 25 | Feb 26, 2026 | ||
| Atari Game Playing | Pitfall | 25 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1k 2012 (val) | 25 | Feb 26, 2026 | ||
| Character-level Language Modeling | Penn Treebank char-level (test) | 25 | Feb 26, 2026 | ||
| Object Detection | MS-COCO 2% labeled protocol | 25 | Feb 26, 2026 | ||
| 3D Lane Detection | Synthetic 3D Lane Dataset rarely observed 1.0 | 25 | Feb 26, 2026 | ||
| 3D Lane Detection | Synthetic 3D Lane Dataset balanced scenes 1.0 | 25 | Feb 26, 2026 | ||
| Age estimation | CACD (test) | 25 | Feb 26, 2026 | ||
| Text-to-Image Generation | COCO 2014 (test) | 25 | Feb 26, 2026 | ||
| Text-to-Speech | LJSpeech (test) | 25 | Jun 25, 2026 |