Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 972 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Link prediction | Power | 28 | May 21, 2026 | ||
| Link prediction | C.ele | 28 | May 21, 2026 | ||
| Link prediction | Yeast | 28 | May 21, 2026 | ||
| Link prediction | PB | 28 | May 21, 2026 | ||
| Link prediction | NS | 28 | May 21, 2026 | ||
| Link prediction | USAir | 28 | May 21, 2026 | ||
| Visual Instruction Following | LLaVA-W | 28 | Feb 26, 2026 | ||
| Instruction Following | IFEval v1 (test) | 28 | May 27, 2026 | ||
| Chinese Knowledge | CEval | 28 | May 15, 2026 | ||
| Forecasting | Solar | 28 | Apr 8, 2026 | ||
| Human Activity Recognition | PAMAP2 (test) | 28 | Mar 4, 2026 | ||
| Segmentation | ACDC (test) | 28 | Jun 4, 2026 | ||
| Long-term Forecasting | ETTh1 v1 (test) | 28 | Apr 28, 2026 | ||
| Information Extraction | SWDE | 28 | Apr 23, 2026 | ||
| Tabular Classification | Adult (test) | 28 | Feb 26, 2026 | ||
| 3D Captioning | Objaverse (test) | 28 | Feb 26, 2026 | ||
| AIGT detection | HC3 PWWS attack, AI to Human (in-domain) | 28 | Feb 26, 2026 | ||
| Document Information Extraction | VRDU Ad-buy Form Mixed Template | 28 | Feb 27, 2026 | ||
| Document Information Extraction | VRDU Ad-buy Form Unseen | 28 | Feb 27, 2026 | ||
| Document Information Extraction | VRDU Registration Form Mixed Template | 28 | Feb 27, 2026 | ||
| Document Information Extraction | VRDU Registration Form (Unseen) | 28 | Feb 27, 2026 | ||
| Document Information Extraction | VRDU Registration Form Single | 28 | Feb 27, 2026 | ||
| Image Classification | CheXpert 5x200 | 28 | May 26, 2026 | ||
| Visual Reasoning | Geometric Shapes | 28 | Feb 26, 2026 | ||
| Bargaining | AmazonHistoryPrice CI 1.0 (test) | 28 | Feb 26, 2026 |