Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2020 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Label shift estimation | MNIST Dirichlet shift alpha=10 (val size=500) | 17 | Apr 3, 2026 | ||
| Label shift estimation | MNIST Dirichlet shift alpha=0.1 (val) | 17 | Apr 3, 2026 | ||
| Label shift estimation | MNIST Dirichlet shift alpha=0.1 size=1500 (val) | 17 | Apr 3, 2026 | ||
| Label shift estimation | MNIST Dirichlet shift alpha=0.1 size=500 (val) | 17 | Apr 3, 2026 | ||
| Prompt Injection Attack Defense | BIPIA | 17 | Jun 1, 2026 | ||
| Classification | PhysioNet Sepsis 2020 (test) | 17 | Apr 3, 2026 | ||
| Relationship prediction ranking | Amazon-Clothing (test) | 17 | Apr 3, 2026 | ||
| Relationship prediction ranking | Amazon-Electronics (test) | 17 | Apr 3, 2026 | ||
| Relationship prediction ranking | Amazon-Movies (test) | 17 | Apr 3, 2026 | ||
| Relationship prediction ranking | Brightkite (test) | 17 | Apr 3, 2026 | ||
| Fraud detection | Amazon Clothing | 17 | Apr 3, 2026 | ||
| Fraud detection | Amazon Electronics | 17 | Apr 3, 2026 | ||
| Fraud detection | Amazon Movies | 17 | Apr 3, 2026 | ||
| Relationship prediction | Amazon Movies | 17 | Apr 3, 2026 | ||
| Question Answering | UMLS Biomedical QA (PubMedQA, BioASQ, ProcBank) (20% test) | 17 | Apr 3, 2026 | ||
| Air quality forecasting | Beijing 3-day forecast | 17 | Apr 2, 2026 | ||
| Air quality forecasting | Beijing 2-day forecast | 17 | Apr 2, 2026 | ||
| Air quality forecasting | Beijing 1-day forecast | 17 | Apr 2, 2026 | ||
| Object Anomaly Detection | Real3D-AD Four Sample per class 1.0 | 17 | Apr 2, 2026 | ||
| Object Anomaly Detection | Real3D-AD Two Sample per class 1.0 | 17 | Apr 2, 2026 | ||
| Player Ranking | 300 Whist games | 17 | Apr 2, 2026 | ||
| Aspect-based Sentiment Analysis | COTE-MFW syntactically perturbed | 17 | Apr 2, 2026 | ||
| Reading Comprehension | SanWen syntactically perturbed | 17 | Apr 2, 2026 | ||
| Question Answering | CMRC syntactically perturbed 2018 | 17 | Apr 2, 2026 | ||
| Natural Language Inference | CMNLI syntactically perturbed | 17 | Apr 2, 2026 |