AI 导读
在 https://t.co/w8mHB85z4n Code Bench 上，该基准衡量真实世界编程性能，GLM-5.3-Flash 在每个 effort 级别都明显优于 GLM-5.2，并与 Claude Opus 4.8 表现相当。https://t.co/UNenXGTwfp
正文
On the https://t.co/w8mHB85z4n Code Bench, which measures real-world coding performance, GLM-5.3-Flash clearly outperforms GLM-5.2 at every effort level and performs on par with Claude Opus 4.8. https://t.co/UNenXGTwfp
来源：@Zai_org · x.com