News for hackers. Stuff that matters.

A comment on Claude Opus 5. Parent comment

Re:Claude Opus 5 by adgjlsfhk1 on Friday July 24, 2026 @04:42PM (#49041329)
Testing at max effort likely doesn't produce optimal results.
[ Parent | on HN ]
Re:Claude Opus 5 by sggyamg on Friday July 24, 2026 @07:00PM (#49042652)
Can you be more explicit?
[ Parent | on HN ]
Re:Claude Opus 5 by adgjlsfhk1 on Friday July 24, 2026 @08:44PM (#49043399)
Max effort is the way to give the highest perf, but not highest perf/$. Having claude (or other models) use a lower effort can often be 80% as smart but get to the results 10x faster for the problems where it works.
[ Parent | on HN ]
Re:Claude Opus 5 by crimist on Friday July 24, 2026 @09:37PM (#49043683)
We've seen models perform worse at higher efforts in our vuln detection evals. For example IIRC gpt 5.5 and 5.6 both scored better or high as compared to xhigh.
[ Parent | on HN ]