Claude Opus 5 vs Claude Opus 4.8: what 9 developers chose.
296 opinions. 9 developers named a direct preference: Claude Opus 4.8 7–2. Approval is 33% vs 49%.
If you want cost & pricing, choose Claude Opus 5. If you want code quality, choose Claude Opus 4.8. The 7–2 direct split is not a landslide; it is a difference in working style.
Choose Claude Opus 5 if you…
- Want a small cost and speed edge
- Can accept weaker reliability and UX scores
- Want the newer model despite lower approval
Choose Claude Opus 4.8 if you…
- Want higher approval and steadier code quality
- Care about UX and reliability
- Weight the 7 to 2 head-to-head split
Cost & pricing for Claude Opus 5. Code quality for Claude Opus 4.8.
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 5 | Claude Opus 4.8 | Mentions |
|---|---|---|---|
| Cost & pricing | +14 | -25 | 7 / 16 |
| Code quality | -20 | +13 | 60 / 62 |
| Reliability | -93 | -48 | 27 / 27 |
| UX | -90 | -50 | 21 / 4 |
| Autonomy | -41 | -20 | 17 / 5 |
| Speed | +20 | -60 | 5 / 5 |
| Usage limits | -100 | -20 | 3 / 5 |
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 5 2 developers
Opus 5 works much better than Opus 4.8 with Sonnet, but its exhausting, jargon-heavy communication makes it hard to understand.
Opus 4.8 was plenty for their work, but they moved to Opus 5 at release and call it better in every way.
Picked Claude Opus 4.8 7 developers
Opus 5 was so bad in real use that they switched back to Opus 4.8.
Prefers Opus 4.8 at work because Opus 5 is too verbose and Opus 4.8 is smart enough.
GLM 5.3 resembles Opus 4.8, which they consider better than Opus 5 and less chatty than DeepSeek V4.
Suspects Anthropic weakened Opus 5 to widen the gap with Fable, so they stayed on Opus 4.8.
The numbers.
| Metric | Claude Opus 5 | Claude Opus 4.8 |
|---|---|---|
| Approval | 33% | 49% |
| Last 90 days | 30% | 57% |
| Opinions | 162 | 134 |
| Developers | 148 | 128 |
| First-hand opinions | 136 | 117 |
| Direct picks | 2 | 7 |
| Type | Model | Model |
| Made by | — | — |
Related matchups.
GPT-5.5 vs Claude Opus 4.8
12–8 direct picks, and a clear difference in what developers optimise for.
Claude Fable 5 vs Claude Opus 4.8
9–3 direct picks, and a clear difference in what developers optimise for.
GPT-5.6 Sol vs Claude Opus 5
7–3 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.