GLM-5.2’s 1M context helped on a large code refactor
GLM-5.2’s showed useful results on a real large codebase. The test used a backend service with about 200,000 lines of code and many links between files. The task was a across roughly 8 files, so the model had to remember early decisions and rules throughout the session.
In many long coding tasks, models start forgetting earlier or contradicting earlier choices around the fifth or sixth file, but this one kept track for longer. It also found a conflict between two services without being directly told to look for it. The downside was speed: it became noticeably slower as the context filled up.
For small one-file edits, it did not feel meaningfully different from a normal model, so the only mattered when the task truly needed the full code picture at once.
Key points
- GLM-5.2’s was tested on a real backend codebase of about 200,000 lines.
- The task changed about 8 files and required the model to remember earlier decisions.
- The model stayed consistent longer than expected during the multi-file .
- It found a conflict between two services on its own.
- The was slower and did not help much for small one-file edits.