News for hackers. Stuff that matters.

A comment on MaxxBench – "Nice DeepSWE score. But is it true?". Parent comment

Re:MaxxBench – "Nice DeepSWE score. But is it true?" by Bolwin on Saturday November 07, 2026 @04:07PM (#50408071)
The benchmark makers and anyone who relies on benchmarks
[ Parent | on HN ]
Re:MaxxBench – "Nice DeepSWE score. But is it true?" by verdverm on Sunday November 08, 2026 @10:19AM (#50414018)
depends, are they optimizing for accuracy or something else?
[ Parent | on HN ]