Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 164 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | PopQA | 86 | Jun 9, 2026 | ||
| Logical Reasoning | ZebraLogic | 86 | Jun 30, 2026 | ||
| Common Sense Reasoning | HellaSwag (test) | 86 | Jun 24, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 86 | Feb 26, 2026 | ||
| Composed Video Retrieval | WebVid-CoVR (test) | 86 | Jun 9, 2026 | ||
| Visual Question Answering | SQA | 86 | Jun 16, 2026 | ||
| Infographic Visual Question Answering | InfoVQA | 86 | Jul 7, 2026 | ||
| Human Activity Recognition | UCI-HAR | 86 | May 22, 2026 | ||
| Unsupervised Object Discovery | COCO 20K | 86 | May 19, 2026 | ||
| Image Classification | Flowers | 86 | Mar 23, 2026 | ||
| Medical Image Segmentation | Duke | 86 | Jun 23, 2026 | ||
| Multi-modal Understanding | LLaVA-Bench Wild | 86 | Apr 14, 2026 | ||
| Super-Resolution | Manga109 x3 (test) | 86 | May 26, 2026 | ||
| Semantic Segmentation | nuScenes 1.0 (val) | 86 | Jul 1, 2026 | ||
| Semantic Segmentation | PST900 | 86 | Jun 16, 2026 | ||
| Fact Verification | TabFact | 86 | Jun 30, 2026 | ||
| Few-shot Image Classification | tieredImagenet (test) | 86 | Feb 26, 2026 | ||
| Image Classification | CIFAR | 86 | May 1, 2026 | ||
| Scene Graph Generation | Open Images V6 (test) | 86 | Jul 8, 2026 | ||
| Monocular Depth Estimation | Stanford2D3D (test) | 86 | May 27, 2026 | ||
| Classification | adult | 86 | May 13, 2026 | ||
| Node Classification | IMDB (test) | 86 | Jul 7, 2026 | ||
| Node Classification | DBLP (test) | 86 | Jul 7, 2026 | ||
| Image Classification | SUN | 86 | Feb 27, 2026 | ||
| Skeleton-based Action Recognition | NTU (Cross-Subject) | 86 | Feb 26, 2026 |