← Back to feed

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

AI · Technology · 2026-10-31 22:46

Memdoor团队利用五个Qwen3.8-27B模型组成的协作系统，在LiveCodeBench Hard基准测试中表现优于Fable 5。

Source: github.com

Auto-generated summary for reference only. RSS