OpenAI· @OpenAI · X·· 2026-06-18AI 评分68
AI 导读
推出 LifeSciBench，一个用于衡量和改进 AI 如何支持现实世界生命科学研究的基准测试。 该基准测试与 173 位来自生物技术和制药研究的科学家共同开发，包含 750 项专家编写的任务，覆盖七个生物学研究工作流程。
正文 · 原文
Introducing LifeSciBench, a benchmark for measuring and improving how well AI supports real-world life science research.
Developed with 173 scientists from biotechnology and pharmaceutical research, LifeSciBench includes 750 expert-authored tasks across seven biological research workflows.
来源：OpenAI · x.com