ModelsOpen Source 🇨🇳 11.08.2026 12:03

Cache Hit Rate Exceeds 98%! ZCode Upgraded to Be the Best Programming Partner for GLM

Zhipu AI's intelligent development tool ZCode has been upgraded, achieving a cache hit rate of over 98% for GLM models in code scenarios. The update enhances coding efficiency and response speed.
Zhipu AI has upgraded its intelligent development tool ZCode, which now delivers a cache hit rate exceeding 98% for GLM models in programming scenarios. This improvement significantly boosts coding efficiency and reduces response latency, making ZCode an optimal companion for developers using GLM. The upgrade focuses on optimizing the caching mechanism to better serve programming tasks.
Source: Zhipu GLM (GNews) — original
Our earlier posts on this topic ↓
Fresh news