Benchmarks: what is being measured
85 AI benchmarks in 15 domains, each with its task, dataset, method, metric, versions and paper. 28 have scores captured here every day.
6 of 85 benchmarks in Knowledge
| Benchmark | Scores | |||
|---|---|---|---|---|
| Knowledge | Sep 7, 20206 years ago | 2009.03300 | · | |
| Knowledge | Jun 3, 20242 years ago | 2406.01574 | 100 | |
| Knowledge | Nov 20, 20232 years ago | 2311.12022 | 100 | |
| Knowledge | Jan 24, 20251 year ago | 2501.14249 | 42 | |
| Knowledge | Nov 7, 20241 year ago | 2411.04368 | · | |
| Knowledge | Sep 8, 20215 years ago | 2109.07958 | · |
Scores counts the models with a captured score on the boards that publish this benchmark. A dot means we capture no board for it yet.
Sources: each benchmark's paper (arXiv) and its official site or leaderboard. Scores are the boards captured here every day, exactly as published.