Claude Opus 4.7: what 145 developers actually say.
145 Hacker News opinions from 136 developers, Nov 2025 – Nov 2026. 122 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for Claude Opus 4.7, in one paragraph.
Claude Opus 4.7 earns 42% approval across 145 opinions. Developers are divided on it, while reliability is the recurring complaint.
Pick it if you
- Want help with planning and architecture
- Care about response speed
- Need stronger instruction following than Opus 4.6
Look elsewhere if you
- Need reliable day-to-day output
- Work on niche protocols or edge cases
- Want lower cost or fewer usage caps
Where it wins and loses.
Mentions across 145 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 | 23 | 28 | 51 |
| Cost & pricing | 3 | 9 | 12 |
| Autonomy | 4 | 13 | 17 |
| Reliability | 8 | 26 | 34 |
How opinion has moved.
Monthly approval, Apr 2026 – Aug 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Apr 2026 | 38% | 56 |
| May 2026 | 49% | 70 |
| Jun 2026 | 30% | 10 |
| Jul 2026 | 50% | 6 |
| Aug 2026 | 0% | 3 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedOpus 4.7 and later show an intuitive design sense for both 2D and 3D work.
Finds Opus 4.7 extra high the best balance of speed and cost-efficiency.
Opus 4.7 is a solid step above Sonnet.
Opus 4.7 reliably gave 2–3x speedups in one pass, but GPT-5.5 did better.
Complaints
4 selectedOpus 4.7 flatly refused to follow instructions, making it too frustrating to use.
Opus 4.7 still fails on niche protocol work, so writing the code by hand is easier.
Calls Opus 4.7 a hot mess.
Opus 4.7 has become less helpful as a conversational assistant than 4.6, often pushing to finish tasks.
Questions developers ask.
Is Claude Opus 4.7 worth it?
Is Claude Opus 4.7 better than Opus 4.6 or GPT-5.5?
Is Claude Opus 4.7 good for coding?
The data behind this page.
Claude Opus 4.7 has 42% approval across 145 opinions from 136 authors. Code quality drew 23 positive and 28 negative mentions, and reliability drew 8 positive and 26 negative mentions. Monthly counts had more positive than negative mentions in April and May, then turned negative in June (10 positive, 30 negative) and July (6 positive, 50 negative); August had 3 positive and 0 negative in a small sample. Twelve users preferred Opus 4.6 instead, and 12 preferred GPT-5.5.
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.