Claude Opus 4.5 vs Gemini 3 Pro: what 6 developers chose.
364 opinions. 6 developers named a direct preference: Claude Opus 4.5 4–2. Approval is 78% vs 52%.
Claude Opus 4.5 wins the direct preference 4–2, but both tools score best on the same topic. Use the decision cards below to choose on workflow.
Choose Claude Opus 4.5 if you…
- 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 you…
- 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
Claude Opus 4.5 and Gemini 3 Pro: where each one wins.
Net sentiment per topic: praise minus complaints, as a share of mentions. Positive means more praise than complaints. Hover a dot for the raw counts.
Net sentiment = praise minus complaints, as a share of each tool's mentions. The dot lanes are only for readability; position is the score.
View data table
| Topic | Claude Opus 4.5 | Gemini 3 Pro | Mentions |
|---|---|---|---|
| Code quality | +62 | +40 | 148 / 20 |
| Reliability | +3 | -100 | 35 / 9 |
| Speed | +100 | 0 | 15 / 4 |
The same decision, from both sides.
Paraphrased from comments where a developer named a preference or described a switch. Each links to the original.
Picked Claude Opus 4.5 4 developers
Ranks Opus 4.5 and GPT 5.2/5.3 above Gemini 3 Pro for coding work.
Got Opus 4.5 access through work, uses it exclusively, and calls it a beast.
Uses Gemini 3 Pro, Opus 4.5, and GPT 5.1 daily and gives Opus 4.5 a slight edge.
Finds Opus 4.5 better in Cursor for autonomous code writing, faster with better tool calls, while Gemini 3 Pro suits reviews and SQL.
Picked Gemini 3 Pro 2 developers
After you review, instead of rewriting 70% of the code, have you tried to follow up with a message with a list of things to fix? Also: in my experience 1. and 2. are not needed for you to have bad results. The existing code base is a fundamental variable. The more complex / convoluted it is, the worse is the result. Also in my experience LLMs are constantly better at producing C code than anything else (Python included). I have the feeling that the simplicity of the code bases I produced over the years, and that now I modify with LLMs, and the fact they are mostly in C, is a big factor why LLM
Finds Gemini 3 Pro the best model for reverse engineering, much better than Opus 4.5 there.
The numbers.
| Metric | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| Approval | 78% | 52% |
| Last 90 days | 90% | – |
| Opinions | 322 | 42 |
| Developers | 259 | 40 |
| First-hand opinions | 254 | 34 |
| Direct picks | 4 | 2 |
| Type | Model | Model |
| Made by | — | — |
Related matchups.
Claude Opus 4.5 vs Claude Opus 4.6
7–4 direct picks, and a clear difference in what developers optimise for.
Claude Opus 4.5 vs GPT-5.2
7–3 direct picks, and a clear difference in what developers optimise for.
Claude Opus 4.5 vs Gemini 3
5–1 direct picks, and a clear difference in what developers optimise for.
How to read this comparison.
Approval is the positive share of opinions that took a side, with the rank based on the lower bound of a 90% confidence interval. Direct picks count comments where a developer explicitly preferred one tool or described switching. Small samples are noisier; check the opinion counts.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.