13:10
2026-09-12
github.com
large-language-models
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard
A training-free method called ledger-based zero-shot self-orchestration lifted open-weight Qwen3.8-27B from 69.2% to 92.4% pass@1 on the 100 latest hard LiveCodeBench problems, slightly exceeding Clau…