Why Nostr? What is Njump?
2025-05-13 02:14:31

foresightnews on Nostr: OpenAI 发布医疗 AI 评估基准 HealthBench Foresight News 消息,OpenAI ...

OpenAI 发布医疗 AI 评估基准 HealthBench

Foresight News 消息,OpenAI 发布医疗 AI 评估基准 HealthBench,并已在 GitHub 开源。该基准由来自全球 250 多名医生共同开发,包含 5000 个真实健康对话,旨在评估大语言模型在医疗场景的表现。
https://foresightnews.pro/news/detail/72597
Author Public Key
npub1yfdayudzpzp4y9zj58v4vj5enqw687jae9yc7gtsjwrhy6p9lnyq4fvg3f