GLM 5: what developers actually say
We read every Hacker News comment from Nov 2025 – Nov 2026 that gave a real opinion on GLM 5. 25 of the 30 opinions come from people who say they use it themselves.
GLM 5 has 78% approval across 30 opinions, 25 of them firsthand, with mixed views counted half. Developers like its code quality (9 positive, 1 negative) and price (5 positive, 1 negative). Reliability draws more doubt (4 positive, 2 negative), including peak-hour slowdowns and one bad provider result. Monthly approval was 90% in February and 70% in March and April; samples from May onward are one opinion each, so there is no reliable recent trend.
Pick it if
- Want strong code quality for the price
- Run agent or app-scripting tasks
- Need more usage for the money
Look elsewhere if
- Need Opus-level code on demanding tasks
- Need steady reliability at peak hours
- Rely on prompt caching to control costs
Strengths and weaknesses
Each row counts opinions that mentioned the topic. Bars to the right of the line are praise, bars to the left are complaints.
How opinion has moved
What developers say
Praise
Complaints
Summaries are paraphrased. Each links to the original comment.
FAQ
Is GLM 5 worth it?
It has 78% approval from 30 opinions. Code quality and price score well, while reliability is mixed. Test it on your own workload before committing.
Is GLM 5 better than Claude Opus 4.6?
The data does not show a clear win. One commenter put it well behind Opus 4.6, and a mixed view placed it near Sonnet on simple to medium tasks. One praise says it beat Claude and Codex on complex backend work.
Is GLM 5 good for coding?
Code quality is its strongest aspect, at 9 positive and 1 negative. Commenters report working code on the first try and strong architecture in a Slack clone test. Some also report tool-use mistakes, verbose output, and poor results through OpenCode.