Claude Opus 4.5 vs Gemini 3: what developers actually say
Based on 392 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
Claude Opus 4.5 comes out ahead on volume, approval, and code quality. It has 322 opinions from 259 authors and 78% approval, including 90% over the last 90 days; Gemini 3 has 70 opinions from 67 authors and 56% approval. Code quality mentions favor Opus 4.5 by 120 to 28, while Gemini 3 sits at 15 to 9, and Gemini 3's reliability mentions are net negative at 2 positive and 9 negative. Pick Gemini 3 when research, PDF extraction, or raw model reasoning matters more than tooling, since one user called it smarter than Opus 4.5 while still preferring Claude Code in practice.
When developers explicitly said they prefer one or switched: 5 picked Claude Opus 4.5, 1 picked Gemini 3.
Choose Claude Opus 4.5 if
- Want 78% approval across 259 authors
- Weight code quality, where it leads 120 to 28
- Want strong autonomy and large-codebase reports
Choose Gemini 3 if
- Need research and PDF extraction
- Want quick UI and app code on small tasks
- Will pair it with tooling you trust
Where each one wins and loses
Why developers switched
Picked Claude Opus 4.5
Picked Gemini 3
Summaries are paraphrased. Each links to the original comment.
Side by side
| Claude Opus 4.5 | Gemini 3 | |
|---|---|---|
| Approval | 78% | 56% |
| Last 90 days | 90% | – |
| Opinions | 322 | 70 |
| First-hand users | 254 | 58 |