GLM-5.2
Z.ai (Zhipu AI)We evaluate Terminal-Bench 2.1 with Claude Code 2.1.167
usedevaluation onlyin GLM-5.2Z.ai
specific method · filed under software implementation
An agentic coding scaffold used to run or evaluate coding models.
The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See agent product for the methods filed beside it.
3 quotes from 3 sources, one card per model, each opening with its strongest.
We evaluate Terminal-Bench 2.1 with Claude Code 2.1.167
SWE-Bench Verified: Tested on internal infrastructure using Claude Code as the scaffolding.
Xiaomi explicitly positions it as a drop-in backend for scaffolds including Claude Code, OpenCode, and Kilo
Picked by hand, not extracted: where to read more, not evidence for anything on this page.