AI 导读
我们已更新 Epoch Capabilities Index（ECI），改用贝叶斯方法。这改进了不确定性估计，让我们能更准确地比较模型，即使它们各自的 ECI 不确定性区间存在重叠。 前沿模型的分数基本未变：强于 GPT-4 的模型平均变动不到 1 个 ECI 点。
正文
We’ve updated the Epoch Capabilities Index (ECI) to use a Bayesian methodology. This improves uncertainty estimates and lets us compare models more accurately, even when their individual ECI uncertainty intervals overlap.
Frontier model scores are largely unchanged: models stronger than GPT-4 move by less than 1 ECI point on average.
来源：Epoch AI · x.com