Claude Opus 4.5 vs Gemini 3 Pro: what developers actually say
Based on 364 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
Claude Opus 4.5 comes out ahead on the evidence: 322 opinions from 259 authors, 78% approval (90% over the last 90 days), and 4 explicit picks against 2 for Gemini 3 Pro. Its code-quality mentions run 120 positive to 28 negative and autonomy 30 to 4, while Gemini 3 Pro's reliability mentions are 0 positive and 9 negative, with complaints about overload and rate limits. Gemini 3 Pro rests on only 42 opinions and 52% approval, so that sample is thin. Choose Gemini 3 Pro when the job is reverse engineering, code review, SQL, design, or small edits, or when you want a fallback once another tool hits its limits.
When developers explicitly said they prefer one or switched: 4 picked Claude Opus 4.5, 2 picked Gemini 3 Pro.
Choose Claude Opus 4.5 if
- You want the strongest code-quality record in the data
- You need autonomous work across large codebases
- You want a large, recent opinion sample behind the choice
Choose Gemini 3 Pro if
- Your work is reverse engineering or codebase review
- You want a second opinion for SQL, design, and small edits
- You need a fallback when another tool hits its limits
Where each one wins and loses
Why developers switched
Picked Claude Opus 4.5
Picked Gemini 3 Pro
Summaries are paraphrased. Each links to the original comment.
Side by side
| Claude Opus 4.5 | Gemini 3 Pro | |
|---|---|---|
| Approval | 78% | 52% |
| Last 90 days | 90% | – |
| Opinions | 322 | 42 |
| First-hand users | 254 | 34 |