ModelsUS vs China01:47Chinese contentScience's Last Exam 基准测试:智能体端到端科研全得 0 分34 家机构出了一套真科研任务考 AI 智能体,最强模型才拿 37.5 分,端到端做研究全是 0 分,能直观看到现在 AI 做科研的真实水平。#Science's Last Exam#Claude Opus 5#AItonomy Foundation#智能体elvis@omarsar0SourceRead laterReadWorth followingUsefulFollow Science's Last Exam