Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 311 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Logical Reasoning | ProofWriter (test) | 57 | May 26, 2026 | ||
| Marine Animal Segmentation | MAS3K (test) | 57 | Jul 7, 2026 | ||
| Referring Remote Sensing Image Segmentation | RRSIS-D (test) | 57 | Jul 7, 2026 | ||
| Super-Resolution | Set14 x3 (test) | 57 | May 19, 2026 | ||
| Mathematical Reasoning | ConceptMath Middle-ZH | 57 | Feb 26, 2026 | ||
| Mathematical Reasoning | ConceptMath Elementary-ZH | 57 | Feb 26, 2026 | ||
| Mathematical Reasoning | ConceptMath Middle-EN | 57 | Feb 26, 2026 | ||
| Mathematical Reasoning | ConceptMath Elementary-EN | 57 | Feb 26, 2026 | ||
| Saliency Detection | PASCAL-Context (test) | 57 | Feb 26, 2026 | ||
| Future Link Prediction | Wikipedia (inductive) | 57 | Jul 7, 2026 | ||
| Virtual Try-On | VITON-HD (test) | 57 | Jun 11, 2026 | ||
| Object Detection | Sim10k to Cityscapes (S2C) | 57 | Jul 1, 2026 | ||
| Classification | OT | 57 | Apr 20, 2026 | ||
| Compositional Zero-Shot Learning | UT-Zappos Closed World | 57 | Mar 18, 2026 | ||
| Model Calibration | Tiny-ImageNet (test) | 57 | Jun 30, 2026 | ||
| Video Moment Retrieval | Charades-STA | 57 | May 29, 2026 | ||
| Image Classification | ImageNet-1k 1.0 (val) | 57 | Feb 26, 2026 | ||
| Visual Question Answering | IconQA | 57 | Mar 30, 2026 | ||
| Geometry Problem Solving | PGPS9K (test) | 57 | Jun 29, 2026 | ||
| Named Entity Recognition | MIT Restaurant | 57 | Apr 23, 2026 | ||
| Calibration | USPS | 57 | May 22, 2026 | ||
| Video Question Answering | ActivityNet (test) | 57 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K (fine-tuning) | 57 | Mar 18, 2026 | ||
| Toxicity Classification | CivilComments sensitive attribute: MUSLIM (test) | 57 | Feb 26, 2026 | ||
| Super-Resolution (4x) | ImageNet | 57 | May 19, 2026 |