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.
5 of 85 benchmarks in Math
| Benchmark | Scores | |||
|---|---|---|---|---|
| Math | Oct 27, 20214 years ago | 2110.14168 | · | |
| Math | Mar 5, 20215 years ago | 2103.03874 | · | |
| Math | · | · | ||
| Math | Nov 7, 20241 year ago | 2411.04872 | · | |
| Math | Oct 6, 20223 years ago | 2210.03057 | · |
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.