François Chollet· @fchollet · X·· 2026-07-25AI 评分51
AI 导读
Opus 5 在 ARC-AGI-3 上创下新 SOTA，达到 30%。 ARC-AGI-3 衡量的是无先验知识解决问题的场景——这正是扩展能力历来收效甚微的领域。令人印象深刻的飞跃！
正文 · 原文
Opus 5 sets a new state-of-the-art on ARC-AGI-3, at 30%.
ARC-AGI-3 measures solving problems with no prior exposure -- the setting where scaling has historically bought the least. Impressive jump!
On ARC-AGI-3, an evaluation where AI models must solve novel problems, Opus 5’s score is three times as high as the next best model.在 X 查看被引用的帖子
来源：François Chollet · x.com