Claude Opus 4.6 vs GPT-5.4: what developers actually say
Based on 401 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
GPT-5.4 comes out ahead overall. Its approval score is 72 vs 63, it wins stated head-to-head picks 10 to 4, and its positive shares are higher for code quality (73% vs 64%), reliability (59% vs 33%), and cost (86% vs 50%). Opus 4.6 has more evidence (287 opinions from 257 authors vs 114 from 105), more autonomy mentions at a similar positive rate (21 positive, 8 negative vs 5 and 2), and better UX sentiment (4 positive, 1 negative vs 1 and 2). Pick Opus 4.6 for instruction-following, analysis and planning, or formatted output; pick GPT-5.4 for coding, reliability, large codebases, and cost control, though its sample is smaller and it has no 90-day approval score.
When developers explicitly said they prefer one or switched: 4 picked Claude Opus 4.6, 10 picked GPT-5.4.
Choose Claude Opus 4.6 if
- Want stronger instruction-following and analysis
- Value formatted output and UX
- Work in Qt C++/QML or want the model to check existing code first
Choose GPT-5.4 if
- Want higher approval and the 10 to 4 head-to-head edge
- Care about reliability, cost, and large-codebase work
- Need a coding model that follows plans to completion
Where each one wins and loses
Why developers switched
Picked Claude Opus 4.6
Picked GPT-5.4
Summaries are paraphrased. Each links to the original comment.
Side by side
| Claude Opus 4.6 | GPT-5.4 | |
|---|---|---|
| Approval | 63% | 72% |
| Last 90 days | 63% | – |
| Opinions | 287 | 114 |
| First-hand users | 242 | 101 |