Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 961 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Math | GSM-Plus | 28 | Jun 1, 2026 | ||
| Time Series Forecasting | ETT (test) | 28 | Mar 26, 2026 | ||
| Robot Manipulation | Fetch-Slide (test) | 28 | Feb 26, 2026 | ||
| Recommendation | Book | 28 | Mar 4, 2026 | ||
| Information Retrieval | TREC DL'20 | 28 | Feb 26, 2026 | ||
| Open-domain Question Answering | TriviaQA (TQA) | 28 | Mar 18, 2026 | ||
| Information Retrieval | Metadata Search Corpus | 28 | Feb 26, 2026 | ||
| Generative Recommendation | Beauty | 28 | Feb 26, 2026 | ||
| Multimodal Document Question Answering | LongDocURL | 28 | Jul 7, 2026 | ||
| Text-to-Video Generation | VideoPhy2 HARD | 28 | May 28, 2026 | ||
| Low-light Image Enhancement | VE-LOL-L v1 (test) | 28 | Feb 26, 2026 | ||
| Gene expression estimation | COAD Visium (multi-cohort) | 28 | Feb 26, 2026 | ||
| Text-to-Image retrieval | Urban1k | 28 | May 13, 2026 | ||
| Pansharpening | QuickBird (QB) reduced-resolution (test) | 28 | Jun 17, 2026 | ||
| Open-Vocabulary Semantic Segmentation | Pascal VOC 2012 (val) | 28 | Feb 26, 2026 | ||
| ROI-level classification | MIST | 28 | Feb 26, 2026 | ||
| ROI-level classification | BCI | 28 | Feb 26, 2026 | ||
| Event-based Video Question Answering | EvQA-Sparse 200 Questions | 28 | Feb 26, 2026 | ||
| Event-based Video Question Answering | EvQA 1000 Questions (full) | 28 | Feb 26, 2026 | ||
| Image Classification | ImageNet-ES-Diverse | 28 | Feb 26, 2026 | ||
| Image Classification | ImageNet ES | 28 | Feb 26, 2026 | ||
| 3D scene generation | 3D-FRONT (test) | 28 | Apr 14, 2026 | ||
| Machine Unlearning | Tiny-ImageNet | 28 | May 12, 2026 | ||
| Image Watermarking | MS-COCO | 28 | Mar 24, 2026 | ||
| Pansharpening | WorldView-3 Full Resolution | 28 | Feb 26, 2026 |