# dsh-dual-model-eval

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

## Metadata

- Author: [@huangdaxianer](https://github.com/huangdaxianer)
- Repo: <https://github.com/huangdaxianer/dsh-dual-model-eval>
- GitHub: [huangdaxianer/dsh-dual-model-eval](https://github.com/huangdaxianer/dsh-dual-model-eval)
- Stars: 0
- Language: TypeScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `agent-evaluation`, `coding-agent`, `deepseek`, `deepseek-harness`, `dsh-plugin`, `git-worktree`, `llm-evaluation`, `model-evaluation`, `multi-agent`, `multi-model`, `side-by-side`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-19T08:34:04.000Z
- Added: 2026-08-19T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:huangdaxianer/dsh-dual-model-eval
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-dual-model-eval](https://deepseek-plugin.org/plugins/huangdaxianer/dsh-dual-model-eval)