GPT-5.5: what developers actually say
We read every Hacker News comment from Nov 2025 – Nov 2026 that gave a real opinion on GPT-5.5. 203 of the 236 opinions come from people who say they use it themselves.
Developers give GPT-5.5 69% approval across 236 opinions from 221 authors, and 203 of those opinions come from firsthand use. Code quality drives the score with 91 positive mentions against 23 negative, and speed is the cleanest signal at 13 to 1. Reliability is close to even at 17 positive and 15 negative, and long sessions after context compaction draw repeated complaints. Approval held at 73 to 74 in May and June, fell to 57 in July, and sits at 67 over the last 90 days on thin recent volume.
Pick it if
- Want high code quality marks (91 positive mentions to 23 negative)
- Care about speed (13 positive to 1 negative)
- Already work in Codex or Copilot and want a cheaper option
Look elsewhere if
- Need steady reliability across long sessions (17 positive to 15 negative)
- Depend on context compaction to keep a plan on track
- Need clean edits without extra indirection or missed formatting steps
Strengths and weaknesses
Each row counts opinions that mentioned the topic. Bars to the right of the line are praise, bars to the left are complaints.
How opinion has moved
What developers say
Praise
Complaints
Summaries are paraphrased. Each links to the original comment.
GPT-5.5 compared
FAQ
Is GPT-5.5 worth it?
Approval sits at 69% across 236 opinions, 203 of them from firsthand use. Code quality is the main reason, at 91 positive mentions against 23 negative. Recent approval is 67 over the last 90 days.
Is GPT-5.5 better than Claude Opus 4.8?
Developers split on it. Twelve preferred GPT-5.5 over Opus 4.8, and eight preferred Opus 4.8. Against Opus 4.7 the gap is wider at 12 to 3, while 8 developers chose Claude Fable 5 over GPT-5.5 against 5 the other way.
Why do developers stop using GPT-5.5?
The common reasons are context compaction losing the thread and edits that add unneeded indirection. A few cite refusals on tool builds and bugs in Elixir. One developer dropped a $200/month plan over usage resets and bugs.