GLM 5.2 vs DeepSeek V4 Pro: what 4 developers chose.
263 opinions. 4 developers named a direct preference: GLM 5.2 4–0. Approval is 75% vs 75%.
If you want code quality, choose GLM 5.2. If you want cost & pricing, choose DeepSeek V4 Pro. The 4–0 direct split is not a landslide; it is a difference in working style.
Choose GLM 5.2 if you…
- Code quality matters most (41 positive mentions vs 31)
- You want the model with more user reports (142 opinions, 109 authors)
- You weight recent satisfaction (82 approval over 90 days vs 67)
Choose DeepSeek V4 Pro if you…
- Cost is the deciding factor (55 positive cost mentions vs 30)
- You want usage-limit headroom (6 positive, 0 negative)
- You run high-volume side projects on a tight budget
Code quality for GLM 5.2. Cost & pricing for DeepSeek V4 Pro.
Net sentiment per topic: praise minus complaints, as a share of mentions. Positive means more praise than complaints. Hover a dot for the raw counts.
Net sentiment = praise minus complaints, as a share of each tool's mentions. The dot lanes are only for readability; position is the score.
View data table
| Topic | GLM 5.2 | DeepSeek V4 Pro | Mentions |
|---|---|---|---|
| Code quality | +74 | +51 | 47 / 41 |
| Cost & pricing | +71 | +90 | 35 / 58 |
| Reliability | -12 | -64 | 16 / 11 |
| Speed | +33 | +67 | 9 / 6 |
| Usage limits | +100 | +100 | 4 / 6 |
The same decision, from both sides.
Paraphrased from comments where a developer named a preference or described a switch. Each links to the original.
Picked GLM 5.2 4 developers
They found DeepSeek V4 Pro at Max reasoning consistently worse than GLM 5.2 at the same setting, which they place near Opus 4.8.
They said DeepSeek V4 Pro used old libraries and cut corners on a detailed spec, with about 80% implemented wrong.
They said GLM 5.2 with max thinking sits between Sonnet 5 and Opus 4.8 and beats DeepSeek.
They reported GLM 5.2 outperforming DeepSeek V4 Pro on Elixir work, though they noted DeepSeek's direct discounted pricing is very cost efficient.
Picked DeepSeek V4 Pro 0 developers
No explicit switches recorded.
The numbers.
| Metric | GLM 5.2 | DeepSeek V4 Pro |
|---|---|---|
| Approval | 75% | 75% |
| Last 90 days | 82% | 67% |
| Opinions | 142 | 121 |
| Developers | 109 | 85 |
| First-hand opinions | 110 | 104 |
| Direct picks | 4 | 0 |
| Type | Model | Model |
| Made by | — | — |
How to read this comparison.
Approval is the positive share of opinions that took a side, with the rank based on the lower bound of a 90% confidence interval. Direct picks count comments where a developer explicitly preferred one tool or described switching. Small samples are noisier; check the opinion counts.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.