François Chollet· @fchollet · X·· 2026-07-07AI 评分47
AI 导读
将基准测试结果报告为标量数字，例如“XYZ 上 75%”，目前完全无意义。你应该总是报告效率分数，例如“每任务成本 $10 下 75%”。
正文 · 原文
Reporting benchmark results as a scalar number, e.g. "75% on XYZ" is completely meaningless at this point. You should always report efficiency scores, e.g. "75% at a cost per task of $10."
来源：François Chollet · x.com