DevConsensus
Comparisons / GLM 5.2 vs DeepSeek V4 Pro
AI models for coding · HN opinions Nov 2025 – Nov 2026

GLM 5.2 vs DeepSeek V4 Pro: what developers actually say

Based on 263 opinions on Hacker News from developers who discussed these two, most of them first-hand users.

GLM 5.2
75%
approval · 142 opinions · 109 developers
last 90 days: 82%
DeepSeek V4 Pro
75%
approval · 121 opinions · 85 developers
last 90 days: 67%

GLM 5.2 comes out ahead overall. It draws more discussion (142 opinions from 109 authors vs 121 and 85), more code-quality praise (41 positive, 6 negative vs 31 and 10), and a higher 90-day approval rate (82 vs 67). Explicit preferences run 4 to 0 for GLM 5.2, and users describe DeepSeek V4 Pro using outdated libraries and breaking changes. DeepSeek V4 Pro is the better pick when cost dominates: 55 positive cost mentions against 3 negative, with reported bills near $24 to $100 a month.

When developers explicitly said they prefer one or switched: 4 picked GLM 5.2, 0 picked DeepSeek V4 Pro.

Choose GLM 5.2 if

  • 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

  • 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

Where each one wins and loses

PraiseComplaintsA = GLM 5.2B = DeepSeek V4 Pro
Code quality
A
6
41
B
10
31
Cost & pricing
A
5
30
B
3
55
Reliability
A
9
7
B
9
2
Speed
A
3
6
B
1
5
Autonomy
A
2
3
Usage limits
A
4
B
6
Open source
A
4

Why developers switched

Picked GLM 5.2

Picked DeepSeek V4 Pro

No explicit switches recorded.

Summaries are paraphrased. Each links to the original comment.

Side by side

GLM 5.2DeepSeek V4 Pro
Approval
75%
75%
Last 90 days82%67%
Opinions142121
First-hand users110104