News for hackers. Stuff that matters.

A comment on DeepSWE: A contamination-free benchmark for long-horizon coding agents.

Re:DeepSWE: A contamination-free benchmark for long-horizon ... by toastmaster11 on Tuesday May 26, 2026 @06:28PM (#48286855)
What happened that placed Opus 4.6 on max reasoning below Sonnet 4.6 on a lowered reasoning level?
[ Parent | on HN ]

There are no comments on this comment yet.