Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1424 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Unlearning | Adult Census Dataset | 21 | Jul 7, 2026 | ||
| Unlearning | Toxic Bias Dataset | 21 | Jul 7, 2026 | ||
| Unlearning | RT-Gender Dataset | 21 | Jul 7, 2026 | ||
| Unlearning | Bios Dataset | 21 | Jul 7, 2026 | ||
| Long-context reasoning | RULER | 21 | Jul 3, 2026 | ||
| Long-context reasoning | LongReason | 21 | Jul 3, 2026 | ||
| Ultrasound Report Generation | Thyroid Ultrasound Examinations | 21 | Jul 3, 2026 | ||
| Function-level code summarization | Selected repositories Obfuscated code (test) | 21 | Jul 3, 2026 | ||
| Function-level code summarization | Selected repositories Clean code (test) | 21 | Jul 3, 2026 | ||
| Hierarchical Code Summarization | Hierarchical Folder Structure | 21 | Jul 3, 2026 | ||
| Sparse Tangent Portfolio Optimization | Nikkei225 (out-of-sample) | 21 | Jul 2, 2026 | ||
| Sparse Tangent Portfolio Optimization | KOSPI200 (out-of-sample) | 21 | Jul 2, 2026 | ||
| Sparse Tangent Portfolio Optimization | FTSE100 (out-of-sample) | 21 | Jul 2, 2026 | ||
| Sparse Tangent Portfolio Optimization | EuroStoxx50 (out-of-sample) | 21 | Jul 2, 2026 | ||
| Question Answering | PopQA | 21 | Jul 2, 2026 | ||
| Question Answering | RetrievalQA | 21 | Jul 2, 2026 | ||
| Question Answering | TriviaQA | 21 | Jul 2, 2026 | ||
| Question Answering | NQ | 21 | Jul 2, 2026 | ||
| Question Answering | DRQA | 21 | Jul 2, 2026 | ||
| Performance Prediction | Reasoning Benchmarks Average | 21 | Jul 2, 2026 | ||
| Visual Object Tracking | DTB70 Rainy | 21 | Jul 2, 2026 | ||
| Visual Object Tracking | GOT-10k Rainy | 21 | Jul 2, 2026 | ||
| Visual Object Tracking | DTB70 Dark | 21 | Jul 2, 2026 | ||
| Visual Object Tracking | GOT-10k Dark | 21 | Jul 2, 2026 | ||
| Visual Object Tracking | DTB70 Foggy | 21 | Jul 2, 2026 |