跳到正文
Artificial Analysis·· 1 天前AI 评分55

Artificial Analysis 上线 HealthBench 与 HealthBench Professional 榜单

HealthBench and HealthBench Professional: Evaluating models in realistic health conversations

AI 导读

Artificial Analysis 推出 HealthBench 和 HealthBench Professional 两个榜单,评估模型在真实健康对话中的表现,前者含 5000 段与普通用户及医护人员的对话,后者为 525 段全部面向临床医生的对话。

来源:Artificial Analysis · artificialanalysis.ai

继续探索 AI