GLM 5.2: what 142 developers actually say.
142 Hacker News opinions from 109 developers, Nov 2025 – Nov 2026. 110 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for GLM 5.2, in one paragraph.
GLM 5.2 earns 75% approval across 142 opinions. Developers praise its code quality. In the last 90 days it sits at 82%.
Pick it if you
- Want strong code quality at a low price
- Run long agent jobs on a small budget
- Want generous usage limits and an open model
Look elsewhere if you
- Need steady output quality across runs
- Need vision or strong prompt adherence
- Need frontier results on the hardest tasks
Where it wins and loses.
Mentions across 142 opinions. Bars are counts, not votes; a tool can be both praised and criticized on the same topic.
View data table
| Topic | Praise | Complaints | Mentions |
|---|---|---|---|
| Code quality | 41 | 6 | 47 |
| Cost & pricing | 30 | 5 | 35 |
| Reliability | 7 | 9 | 16 |
How opinion has moved.
Monthly approval, Jun 2026 – Oct 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Jun 2026 | 72% | 55 |
| Jul 2026 | 74% | 59 |
| Aug 2026 | 79% | 21 |
| Sep 2026 | 83% | 3 |
| Oct 2026 | 100% | 4 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedHad a good month or two with GLM 5.2, roughly Opus 4.5 level in capability.
They enjoyed using GLM 5.2 more than the newer 5.3 version.
Switched to GLM 5.2 and is glad to leave the big frontier providers, despite mixed feelings about z.ai.
GLM 5.2 was the only model that helped while agents tried to access a site.
Complaints
4 selectedGLM 5.2 is capable but burns so many tokens that its pricing is misleading.
GLM 5.2 is inconsistent, with much more output-quality variance than the best US models.
Shares an SVG test where GLM 5.2 still trails Opus, with structurally poor output.
These models behave dumb and ignore instructions, even when writing their own skills.
Questions developers ask.
Is GLM 5.2 worth it?
Is GLM 5.2 better than Claude Opus?
Is GLM 5.2 good for coding?
The data behind this page.
Developers give GLM 5.2 a 75% approval score across 142 opinions from 109 authors, and 110 of those opinions come from firsthand use. Code quality is the strongest point at 41 positive mentions against 6 negative, with cost next at 30 against 5. Approval over the last 90 days is 82%, up from 72% in June 2026, but opinion volume fell from 59 in July to 3 in September and 4 in October, so the recent gain rests on thin data. Reliability is the weak spot at 7 positive against 9 negative, and some users report token burn that cancels out the low price.
Every number comes from public Hacker News comments collected through the HN Search API. A language model tagged each comment for sentiment, first-hand use, topic and switches; a human spot-checks samples. No vendor can pay for placement.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.