typed-decision-bench
kyr0/typed-decision-bench
Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.
- 星标
- 0
- 派生
- 0
收录依据
typed-decision-bench 为实现 System One 类型化决策 API 的系统提供评测和校准套件,可用于 Jev 兼容请求;README 描述了大规模留出集,本次未复现实验结果。