Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1908 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-modal Representation Learning | MMEB In-Distribution 1.0 | 18 | Feb 26, 2026 | ||
| Multi-modal Representation Learning | MMEB Overall 1.0 | 18 | Feb 26, 2026 | ||
| Graph Explanation | IMDB | 18 | Feb 26, 2026 | ||
| Graph Explanation | DBLP | 18 | Feb 26, 2026 | ||
| Link Prediction | Collaboration CS (test) | 18 | Feb 26, 2026 | ||
| Link Prediction | Collaboration NS (test) | 18 | Feb 26, 2026 | ||
| Link Prediction | Web (PB) (test) | 18 | Feb 26, 2026 | ||
| Link Prediction | Transport (USAir) (test) | 18 | Feb 26, 2026 | ||
| Link Prediction | Biology C.ele (test) | 18 | Feb 26, 2026 | ||
| Text Classification | IMDB (test) | 18 | Feb 26, 2026 | ||
| Text Classification | CoLA (test) | 18 | May 19, 2026 | ||
| Detection Evasion | MAGE | 18 | Jun 2, 2026 | ||
| Node Classification | WikiCS (evaluation nodes) | 18 | Feb 26, 2026 | ||
| Node Classification | PubMed (evaluation nodes) | 18 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | CelebA (In) CIFAR-10 (Out) (test) | 18 | May 22, 2026 | ||
| Out-of-Distribution Detection | FashionMNIST (In) / MNIST (Out) (test) | 18 | Jun 15, 2026 | ||
| Visual Mathematical Reasoning | MathVista | 18 | Mar 4, 2026 | ||
| Commonsense Question Answering | CSQA | 18 | Feb 26, 2026 | ||
| Ride-hailing TSH Prediction | Ride-hailing dataset 2023 (test) | 18 | Feb 26, 2026 | ||
| Ride-hailing Call Prediction | Ride-hailing dataset 2023 (test) | 18 | Feb 26, 2026 | ||
| Ride-hailing TSH Prediction | Ride-hailing dataset 2024 (test) | 18 | Feb 26, 2026 | ||
| Ride-hailing Call Prediction | Ride-hailing dataset 2024 (test) | 18 | Feb 26, 2026 | ||
| Ride-hailing TSH Prediction | Ride-hailing dataset 2025 (test) | 18 | Feb 26, 2026 | ||
| Ride-hailing Call Prediction | Ride-hailing dataset 2025 (test) | 18 | Feb 26, 2026 | ||
| Information-seeking | Xbench-DS | 18 | Feb 26, 2026 |