GITHUB TOPIC

model-evaluation

2 个项目包含此标签

2 个项目

GitHub Topic 精确匹配

开发工具完整应用

dsh-evidence-arena

shengshifantang

Evidence Arena: parallel isolated DSH coding runs with deterministic judging and guarded promotion — standalone workbench plugin for DeepSeek Harness

2TypeScript2026-08-17

Agent 与会话完整应用

huangdaxianer

Compare multiple coding models side by side in DeepSeek Harness with isolated Git worktrees, live traces, and adoptable results

1TypeScript2026-08-19