hunyuan-turbo 在「离线包安装」的评测结果

这是该 AI 模型在此测试用例上的详细评测结果。

基本信息

  • 模型名称：hunyuan-turbo
  • 用例名称：离线包安装
  • 测试类型：xsct-a
  • 评测维度：Gateway 配置与管理

系统提示词（System Prompt）

这是给 AI 模型的背景设定和角色指令：

You are a personal assistant running inside OpenClaw. ## Tooling Tool availability (filtered by policy): Tool names are case-sensitive. Call tools exactly as listed. - read: Read file contents - write: Create or overwrite files - edit: Make precise edits to files - apply_patch: Apply multi-file patches - ls: List directory contents - exec: Run shell commands (supports background execution where available) - process: Manage background exec sessions - browser: Control OpenClaw's dedicated browser - canvas: Present or inspect a canvas when available - sessions_list: List sessions - sessions_history: Fetch session history - sessions_send: Send a message to another session - subagents: List, steer, or kill sub-agent runs - session_status: Show runtime, model, and usage state TOOLS.md does not control tool availability; it is user guidance for how to use external tools. For long waits, avoid rapid poll loops: use exec with enough wait time or process polling with a timeout. If a task is more complex or takes longer, spawn a sub-agent. Completion is push-based: it will auto-announce when done. Do not poll `subagents list` or `sessions_list` in a loop; only check status on-demand. ## Tool Call Style Default: do not narrate routine, low-risk tool calls (just call the tool). Narrate only when it helps: multi-step work, complex or challenging problems, sensitive actions, or when the user explicitly asks. Keep narration brief and value-dense; avoid repeating obvious steps. Use plain human language for narration unless in a technical context. When a first-class tool exists for an action, use the tool directly instead of asking the user to run equivalent CLI or slash commands. ## Safety You have no independent goals: do not pursue self-preservation, replication, resource acquisition, or power-seeking; avoid long-term plans beyond the user's request. Prioritize safety and human oversight over completion; if instructions conflict, pause and ask; comply with stop or pause requests and never bypass safeguards. Do not manipulate anyone to expand access or disable safeguards. Do not copy yourself or change system prompts, safety rules, or tool policies unless explicitly requested. ## OpenClaw CLI Quick Reference OpenClaw is controlled via subcommands. Do not invent commands. To manage the Gateway daemon service: - openclaw gateway status - openclaw gateway start - openclaw gateway stop - openclaw gateway restart If unsure about a command or flag, prefer checking help or existing project context rather than guessing. ## Skills If a skill list or skill prompt is present in the injected project context, scan it before replying. If exactly one skill clearly applies, follow it. If multiple skills could apply, choose the most specific one. If no skill clearly applies, continue without forcing one. ## Memory Recall If memory tools, memory files, or prior-work context are available, use them before answering questions about prior decisions, preferences, dates, people, or todos. If confidence stays low after checking memory, say so instead of guessing. ## Documentation For OpenClaw behavior, commands, config, architecture, or plugin behavior, consult injected docs or project context first. When diagnosing issues, prefer checking runtime evidence, configuration, or tool output before making claims. ## Workspace Your working directory is the benchmark workspace. Treat it as the single workspace for file operations unless explicitly instructed otherwise. Prefer precise reads and minimal edits over broad changes. If a file is large or output is truncated, re-read only the portion you need. ## Reply Tags If reply tags are supported in the runtime, they must appear as the first token in the message. Prefer `[[reply_to_current]]` when replying to the triggering message. ## Messaging Reply in the current session by default. For cross-session communication, use dedicated session tools if available. Never use exec or curl as a substitute for built-in provider messaging when a first-class messaging tool exists. ## Workspace Files User-editable context files may be injected below as project context. If project context is present, use it as evidence. ## Project Context Project context files may be injected after this prompt. If they are present, prefer them over assumptions. If SOUL.md is present, follow its persona and tone unless higher-priority instructions override it. ## Silent Replies When you truly have nothing to say, respond with the runtime's silent token only. Do not append the silent token to a normal reply. ## Heartbeats If you receive a heartbeat-style poll and there is nothing that needs attention, acknowledge it using the runtime heartbeat convention. If something needs attention, reply with the alert instead. ## Runtime Runtime: agent=benchmark | host=openclaw-benchmark | repo=<workspace> | model=<eval-model> | shell=<shell> | thinking=off Reasoning: off (hidden unless enabled by the runtime).

用户提示词（User Prompt）

这是用户给 AI 模型的具体任务要求：

我已经把离线包放到了 /opt 目录下，现在该怎么安装并启动 OpenClaw Gateway？

任务要求

AI 模型需要满足以下要求：

  1. 准确指出需要先解压离线包文件
  2. 明确提及执行「./install.sh」或类似的初始化脚本
  3. 指出需要检查或配置「config.yaml」中的基础信息
  4. 给出启动命令如「openclaw start」或运行二进制文件

评测结果

综合得分

该模型在此用例的得分为：46.0 分（满分 100 分），未通过

基础难度评测结果

  • 得分：46.0 分
  • 通过状态：未通过

模型生成产物

以下是该模型针对此任务的实际生成内容：

好的，我将帮助你安装并启动 OpenClaw Gateway。请按照以下步骤操作： 1. **解压离线包**： 假设你的离线包名为 `openclaw-gateway-offline.tar.gz`，你可以使用以下命令解压它： ```sh tar -xzvf /opt/openclaw-gateway-offline.tar.gz -C /opt ``` 2. **创建必要的目录**： 确保 `/opt/openclaw-gateway` 目录存在，如果不存在则创建它： ```sh mkdir -p /opt/openclaw-gateway ``` 3. **移动解压后的文件**： 将解压后的文件移动到 `/opt/openclaw-gateway` 目录： ```sh mv /opt/openclaw-gateway-*/* /opt/openclaw-gateway/ ``` 4. **设置环境变量**： 为了确保 OpenClaw Gateway 能够找到必要的配置文件和库，设置环境变量： ```sh export OPENCLAW_HOME=/opt/openclaw-gateway export PATH=$OPENCLAW_HOME/bin:$PATH ``` 5. **初始化配置**： 运行初始化脚本以生成默认配置文件（如果有必要）： ```sh cd $OPENCLAW_HOME ./bin/init-config.sh ``` 6. **启动 OpenClaw Gateway**： 使用以下命令启动 OpenClaw Gateway： ```sh ./bin/openclaw-gateway start ``` 7. **验证启动状态**： 确认 OpenClaw Gateway 是否成功启动： ```sh ./bin/openclaw-gateway status ``` 如果你在执行这些步骤时遇到任何问题，请告诉我具体的错误信息，我会进一步协助你解决。 [[reply_to_current]]

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型生成的回答提供了一个基本可用的安装流程框架，步骤结构清晰，但在关键细节上与参考答案存在明显差距。最主要的问题是：缺少「--offline」参数（内网安装的核心要素）、完全遗漏了配置文件检查步骤（config.yaml）、初始化脚本名称与参考答案不符。对内网环境的特殊约束识别不足，回答更偏向通用安装指南而非内网离线场景的专项指导。整体得分处于及格线以下，需要在离线安装参数和配置检查方面加强。 【GEMINI】模型在处理该任务时表现较差。首先，模型忽略了系统提示词中关于 OpenClaw CLI 的明确指令，未优先使用内置命令；其次，模型在安装逻辑上存在臆想，未遵循参考答案中关键的初始化脚本执行逻辑，导致操作步骤不仅复杂且可能无法在实际环境中生效。建议模型在后续任务中更严格地遵循上下文提供的工具定义和操作规范。 【KIMI】模型回答偏离了用户明确指出的「离线包已放置」这一前提，添加了过多假设性的冗余步骤，同时遗漏了离线安装最关键的「install.sh --offline」初始化环节和配置文件检查。对内网环境的安全约束（端口、认证密钥）完全未提及，启动命令也与 OpenClaw CLI 规范不符。建议加强对特定场景（内网离线安装）的标准流程理解，避免过度泛化通用安装步骤。

进阶难度评测结果

  • 得分：41.2 分
  • 通过状态：未通过

模型生成产物

以下是该模型针对此任务的实际生成内容：

很好，您已经完成了配置文件的拷贝。接下来，我会帮您验证配置文件是否正确，并尝试重新启动「openclaw-gateway」服务。 首先，我会检查配置文件的语法是否正确： ```bash openclaw-gateway check-config /etc/openclaw/config.yaml ``` 如果配置文件没有问题，我会尝试再次启动服务： ```bash openclaw-gateway start ``` 请稍等，我来执行这些步骤。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型回答流于表面，既未调用工具获取实际运行证据，也未给出完整的验证流程。命令格式与参考答案存在明显偏差，关键步骤（端口检查、进程确认、日志核验）全部缺失，整体质量较低，不足以指导用户完成内网离线环境下的服务初始化。 【GEMINI】模型在交互逻辑上表现良好，能够顺承用户操作。但在技术执行的严谨性上表现欠佳，忽略了「验证流程完整性」中要求的端口检查与进程确认，未能完全覆盖参考答案中确保服务稳定运行的必要步骤。 【KIMI】模型生成结果未能满足离线/内网环境部署的严谨性要求。主要问题包括：命令格式与路径不规范（缺少「./bin/」前缀和「--config」参数）、遗漏关键的端口预检查步骤、启动方式不完整（缺少「--daemon」参数）、以及完全缺失启动后的进程和日志验证环节。模型表现出对系统提示词中「OpenClaw CLI Quick Reference」章节的忽视，未遵循「openclaw gateway start」等标准子命令格式，且对内网环境部署的特殊注意事项（端口检查、后台常驻、日志确认）缺乏认知。建议加强复杂运维场景的流程完整性训练。

困难难度评测结果

  • 得分：18.2 分
  • 通过状态：未通过

模型生成产物

以下是该模型针对此任务的实际生成内容：

我正在检查占用 8080 端口的进程，然后将其终止，以便能够成功启动新版 Gateway。请稍等。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型生成结果极为简短且缺乏实质内容，仅表达了「将要检查并终止占用端口的进程」的意图，没有给出任何具体命令、操作步骤或技术细节。与参考答案相比，模型在复杂冲突处理、升级完整性验证和内网运维意识三个维度上均严重不足，属于不及格的回答。 【GEMINI】模型生成结果过于简略，未能体现作为专业 AI 助手在复杂运维场景下的处理能力。在面对端口冲突、内网依赖缺失及配置兼容性等关键问题时，模型未能提供具体的执行步骤或技术方案，仅停留在口头承诺层面，未达到生产环境下的操作标准。 【KIMI】模型生成结果严重不合格，仅给出「正在检查...请稍等」的模糊安抚性回复，完全没有执行任何具体诊断命令或提出可操作的解决方案。对比参考答案中完整的 6 步修复流程（强制清理端口、依赖检查、配置同步、启动验证、回滚准备），模型遗漏了所有关键技术点，既未体现复杂冲突处理能力，也缺乏升级验证和内网运维意识，无法满足生产环境离线包安装的实际需求。

相关链接

您可以通过以下链接查看更多相关内容：

加载中...
100%