Chuyển đến nội dung chính

benchmark 6

  • oh-my-knowledge v0.54.0 Đã xác minh 18

    OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.

    dsh plugin add oh-my-knowledge
  • dsh-excel-chat v0.34.1 Đã xác minh Giao diện web 6

    Talk to Excel in DeepSeek Harness: create/edit spreadsheets, formulas, styles, filters, and tables by conversation; auto-verifies formulas after every edit, repairs silent errors, and validates charts.

    dsh plugin add dsh-excel-chat
  • dsh-bench v0.1.0 Đã xác minh 2

    虚拟 DSH 环境跑分机 — 插件/Skill 加载与工具调用基准(L1 零 token)。dsh-plugin-hub 生态的可扩展类插件:为 hub 提供独立性能评分(加载/工具调用各环节耗时)。

    dsh plugin add dsh-bench
  • dsh-eval v0.3.0 Đã xác minh 2

    Agent evaluation platform: benchmark YAML, headless run orchestration, trace-based metrics, and run reports

    dsh plugin add dsh-eval
  • dsh-trapstreet v0.6.0 Đã xác minh 1

    Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run

    dsh plugin add @trapstreet/dsh-trapstreet
  • dsh-minecraft v0.12.2 Đã xác minh 1

    Play Minecraft from DeepSeek Harness: the agent observes, moves, mines and crafts through tools backed by a live Mineflayer bot

    dsh plugin add dsh-minecraft