GPT-5.5 vs Claude Opus 4.8: what developers actually say
Based on 370 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
GPT-5.5 comes out ahead overall. It has 236 opinions from 221 authors and 69% approval, versus 134 opinions from 128 authors and 49% for Opus 4.8; 90-day approval is 67% against 57%. Its positive-to-negative balances are stronger for code quality (91 to 23 versus 35 to 27), cost (10 to 8 versus 6 to 10), and speed (13 to 1 versus 1 to 4), and explicit picks run 12 to 8 in its favor. Opus 4.8 is the better pick for readable code, intent-sensitive tasks, and Figma or data-analysis work, but its reliability balance is 7 positive to 20 negative and its usage-limit balance is 2 to 3.
When developers explicitly said they prefer one or switched: 12 picked GPT-5.5, 8 picked Claude Opus 4.8.
Choose GPT-5.5 if
- Want the stronger overall and 90-day approval record
- Prioritize speed and lower cost
- Want the larger firsthand evidence base
Choose Claude Opus 4.8 if
- Prefer code that is easier to review
- Need the model to grasp intent on Figma or data work
- Can tolerate slower responses, higher cost, and tighter limits
Where each one wins and loses
Why developers switched
Picked GPT-5.5
Picked Claude Opus 4.8
Summaries are paraphrased. Each links to the original comment.
Side by side
| GPT-5.5 | Claude Opus 4.8 | |
|---|---|---|
| Approval | 69% | 49% |
| Last 90 days | 67% | 57% |
| Opinions | 236 | 134 |
| First-hand users | 203 | 117 |