DeepSeek HarnessHub
提交插件

hj01857655/dsh-model-arena ↗★ 0

dsh-model-arena

在多个模型中运行相同提示词的对比工具 适合需要直观对比不同模型生成效果的评测与开发任务。

其他擴充
套件
dsh-model-arena
相容性
待驗證
Cordis 依賴範圍
^4.0.1
版本
0.5.1
授權
MIT
最近更新
2026年9月19日

安裝

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hj01857655/dsh-model-arena

說明文件

閱讀完整 README ↗

dsh-model-arena

npm version npm downloads CI license node GitHub stars dsh plugin

Run the same prompt through every model you have, and see the difference without squinting.

Install

dsh plugin --profile web add dsh-model-arena

What it does

  • Run a prompt through N models. Same prompt, identical parameters, outputs collected side by side.
  • Compare. Line-level diff between any two model outputs.
  • Score. Auto-scorer (length, latency, reference match) + manual user ratings (1-5).
  • Benchmark suites. Save a named set of prompts + models, re-run after changes, get a regression report.
  • Panel. Settings page listing recent runs with drill-down to comparison view.

CLI

dsh-model-arena list                              # list recent runs
dsh-model-arena compare      # diff two models in a run
dsh-model-arena rate  --model M --rating 4   # rate a model output

License

MIT