Comparisons / Claude Opus 4.5 vs Claude Opus 4.6
AI models for coding · HN opinions Nov 2025 – Nov 2026
Claude Opus 4.5 vs Claude Opus 4.6: what developers actually say
Based on 609 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
Claude Opus 4.5 comes out ahead on most measures. Its approval is 78 versus 63 for Opus 4.6, and 90 over the last 90 days versus 63; code quality runs 120 positive to 28 negative against 78 to 43, and reliability 18 to 17 against 19 to 39. Opus 4.6 shows a narrow UX edge at 4 positive to 1 negative and draws praise for following negative instructions. Choose Opus 4.6 when rule-following matters more than reliability, speed, and cost.
When developers explicitly said they prefer one or switched: 7 picked Claude Opus 4.5, 4 picked Claude Opus 4.6.
Choose Claude Opus 4.5 if
- Want higher approval (78 vs 63)
- Care about code quality sentiment (120 positive vs 28 negative)
- Prefer short, instruction-heavy interactive sessions
Choose Claude Opus 4.6 if
- Need better following of negative instructions
- Weight UX comments, where it leads 4 to 1
- Want the Opus release 12 users ranked above Opus 4.7
Where each one wins and loses
PraiseComplaintsA = Claude Opus 4.5B = Claude Opus 4.6
Code quality
Reliability
Autonomy
Large codebases
Speed
Cost & pricing
UX
Usage limits
Why developers switched
Picked Claude Opus 4.5
Said 4.6 overthought tasks and spun for long stretches while 4.5 stayed responsive, so they skipped later releases.HN comment · Jun 22, 2026
Argued Anthropic tuned 4.6 for cost rather than capability and called it a bad model after 4.5 handled longer tasks well.HN comment · May 28, 2026
Preferred 4.5 for fine-grained instruction workflows and saw 4.6 as a regression tuned for long-running, less interactive tasks.HN comment · Apr 18, 2026
Found 4.6 post-trained to patch code quickly, producing sloppy fixes that showed it did not understand the problem.HN comment · Apr 6, 2026
Recommended 4.5 over 4.6 because 4.6 gets very expensive once its larger context window fills.HN comment · Mar 7, 2026
Felt 4.6 was worse than 4.5 had been in late 2025 and still reached for the older model.HN comment · Feb 19, 2026
Picked Claude Opus 4.6
Said 4.6 was a significant step up from 4.5 and that staying on 4.5 would have meant worse results and slower shipping.HN comment · Apr 18, 2026
Said 4.5 improved sharply over earlier models and 4.6 improved again, with the pace of gains increasing.HN comment · Feb 17, 2026
Found 4.6 better than 4.5 at following instructions, especially negative rules, and at applying skills.HN comment · Feb 9, 2026
Summaries are paraphrased. Each links to the original comment.
Side by side
| Claude Opus 4.5 | Claude Opus 4.6 | |
|---|---|---|
| Approval | 78% | 63% |
| Last 90 days | 90% | 63% |
| Opinions | 322 | 287 |
| First-hand users | 254 | 242 |