AI 导读
GLM-5.3 达到 310 tok/s！ Databricks 推理在速度和延迟上再次双双排名第一。 在我们内部的 Databricks 编程基准测试中，GLM-5.3 是最强的开源编程模型，可与 Fable 5 和 Opus 4.8 相媲美。https://t.co/3CS00aFIsf
正文
GLM-5.3 at 310 tok/s!
Databricks inference is #1 in both speed and latency, again.
On our internal Databricks coding benchmark, GLM-5.3 is the strongest OSS model for coding, competitive with Fable 5 and Opus 4.8. https://t.co/3CS00aFIsf
来源：@Yuchenj_UW · x.com