Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1922 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-Hop Question Answering | Bamboogle | 18 | Feb 26, 2026 | ||
| Multi-Hop Question Answering | MuSiQue | 18 | Feb 26, 2026 | ||
| Multi-Hop Question Answering | HotpotQA | 18 | Feb 26, 2026 | ||
| General Question Answering | TriviaQA | 18 | Feb 26, 2026 | ||
| Early Rumor Detection | Twitter-COVID-19 (test) | 18 | Feb 26, 2026 | ||
| Data Science Task Automation | xBench-DS | 18 | Feb 26, 2026 | ||
| Web-based Question Answering | WebWalkerQA | 18 | Feb 26, 2026 | ||
| Node Classification | Pubmed (high-label) | 18 | Feb 26, 2026 | ||
| Node Classification | Pubmed low-label | 18 | Feb 26, 2026 | ||
| Node Classification | Cora (high-label) | 18 | Feb 26, 2026 | ||
| Node Classification | Cora (low-label) | 18 | Feb 26, 2026 | ||
| Coreference Resolution | XWinograd French | 18 | Apr 23, 2026 | ||
| Natural Language Inference | XNLI French | 18 | Apr 23, 2026 | ||
| Code Reasoning | LiveCodeBench 1.0 (test) | 18 | Feb 26, 2026 | ||
| Scientific Reasoning | GPQA 1.0 (test) | 18 | Feb 26, 2026 | ||
| Multilingual Knowledge | MMMLU | 18 | Feb 26, 2026 | ||
| Hallucination Detection | SQuAD | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 25 | 18 | Apr 6, 2026 | ||
| Uncertainty Calibration | GPQA diamond | 18 | Feb 26, 2026 | ||
| Uncertainty Calibration | GPQA main | 18 | Feb 26, 2026 | ||
| Uncertainty Calibration | SciBench | 18 | Feb 26, 2026 | ||
| Uncertainty Calibration | MATH 500 | 18 | Feb 26, 2026 | ||
| Math | IMO-ANSWERBENCH | 18 | Jul 2, 2026 | ||
| Multilingual Retrieval-Augmented Generation | MKQA 1.0 (test) | 18 | Feb 26, 2026 | ||
| Personalized Reward Modeling | BESPOKE-Meta OOD | 18 | Feb 26, 2026 |