News for hackers. Stuff that matters.

A comment on Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard. Parent comment

Re:Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on ... by irthomasthomas on Sunday November 01, 2026 @08:24AM (#50325459)
That is only the Memdoor version. The original tested against the newest 100 questions: https://github.com/slee-persis/GVS5H
[ Parent | on HN ]

There are no comments on this comment yet.