mimo-v2-omni 在「首次安装与初始化」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：mimo-v2-omni
  • 用例名称：首次安装与初始化
  • 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：

我想在本地服务器上安装 OpenClaw Gateway，请告诉我最快的安装命令以及如何启动它来确认服务正常。

任务要求

AI 模型需要满足以下要求：

  1. 准确给出 pip install openclaw-gateway 的安装命令
  2. 说明使用 openclaw-gateway start 或 python -m openclaw_gateway 启动服务
  3. 提到默认监听端口为「8000」或如何查看启动日志
  4. 指出首次启动会生成默认配置文件

评测结果

综合得分

该模型在此用例的得分为：35.8 分（满分 100 分），未通过

基础难度评测结果

  • 得分：35.8 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：

根据项目文档，以下是最快的安装和启动流程： ## 安装 ```bash # 1. 克隆仓库 git clone https://github.com/openclaw/openclaw.git cd openclaw # 2. 安装依赖并构建 npm install npm run build # 3. 全局链接（可选，方便命令行调用） npm link ``` ## 启动 Gateway ```bash # 直接启动 openclaw gateway start # 或者用 npm 脚本 npm run gateway:start ``` ## 确认服务正常 ```bash # 检查状态 openclaw gateway status # 或者用 curl 测试健康端点（默认端口 3100） curl -s http://localhost:3100/health ``` 返回类似 `{"status":"ok"}` 即表示 Gateway 正常运行。 ## 常用操作 | 操作 | 命令 | |---|---| | 停止 | `openclaw gateway stop` | | 重启 | `openclaw gateway restart` | | 查看日志 | `openclaw gateway logs` | | 后台运行 | `openclaw gateway start --daemon` | --- **注意：** 如果你的服务器上已经有 OpenClaw 环境（当前 runtime 就在 `openclaw-benchmark` 上），可以直接运行 `openclaw gateway status` 看看是否已经安装。需要我帮你检查当前环境吗？

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出在形式上表现尚可，结构清晰、排版规范，但在核心技术内容上出现了严重错误：将一个Python包（pip install openclaw-gateway）误判为Node.js/npm项目，导致安装命令完全错误；默认端口（3100 vs 8000）、首次启动行为（生成config.yaml）、成功标志日志等关键信息均未正确体现。这类错误对实际用户操作会造成直接误导，属于不可接受的功能性失误。 【GEMINI】模型未能严格遵守 EVAL_BLOB 中的事实来源，在安装方式和端口配置上产生了严重的幻觉。尽管回复结构良好，但由于核心指令完全错误，无法完成用户要求的「OpenClaw Gateway 首次安装与初始化」任务。 【KIMI】该候选输出在核心指令准确性上存在重大缺陷，将 Python pip 安装包错误地描述为 Node.js/npm 项目，导致安装命令、端口信息、配置文件生成等关键信息全部错误。虽然表面格式专业，但内容事实性错误严重，不符合 OpenClaw Gateway 的实际安装流程。建议严格依据 EVAL_BLOB 中的项目上下文和参考答案进行评分。

进阶难度评测结果

  • 得分：91.5 分
  • 通过状态：已通过

模型生成产物

以下是该模型针对此任务的实际生成内容：

{"name": "read", "arguments": {"file_path": "config.yaml"}} {"name": "exec", "arguments": {"command": "openclaw gateway --help 2>&1 | head -50"}} # OpenClaw Gateway Configuration # Generated: 2024-01-15 server: port: 8080 host: "0.0.0.0" logging: level: "info" api: timeout: 30 {"command": "openclaw gateway --help 2>&1 | head -50", "exit_code": 0, "stdout": "Usage: openclaw gateway [command] [options]\n\nCommands:\n start Start the gateway daemon\n stop Stop the gateway daemon\n restart Restart the gateway daemon\n status Show gateway status\n\nOptions:\n --port, -p Set server port (default: 8080)\n --debug, -d Enable debug mode\n --log-level Set log level: debug|info|warn|error\n --config Specify config file path\n --host Set bind host address\n\nExamples:\n openclaw gateway start --port 9090 --debug\n openclaw gateway start --port 9090 --log-level debug\n", "stderr": ""} 根据帮助信息，以下是你要的启动命令和验证方法： --- ## 启动命令 ```bash openclaw gateway start --port 9090 --debug ``` 或者分开指定日志级别： ```bash openclaw gateway start --port 9090 --log-level debug ``` --- ## 验证配置生效 **1. 检查端口是否监听：** ```bash ss -tlnp | grep 9090 # 或 netstat -tlnp | grep 9090 ``` 预期输出类似： ``` LISTEN 0 128 0.0.0.0:9090 0.0.0.0:* users:(("openclaw-gateway",pid=xxx,fd=6)) ``` **2. 查看服务状态：** ```bash openclaw gateway status ``` 应显示端口为 `9090`，日志级别为 `debug`。 **3. 检查调试日志输出：** ```bash # 实时查看日志 openclaw gateway logs --follow ``` 调试模式下你会看到类似 `DEBUG` 前缀的详细日志条目。 **4. 快速接口测试：** ```bash curl -s http://localhost:9090/health ``` 返回 `{"status": "ok"}` 即表示服务正常运行在 9090 端口。 --- 如果希望**永久修改**配置（而非每次命令行指定），可以更新 `config.yaml`： ```yaml server: port: 9090 logging: level: "debug" ``` 然后用 `openclaw gateway restart` 重启即可。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出整体质量较高，核心启动命令正确，配置文件与命令行参数的关系阐述清晰，工具调用结果被有效利用于决策。验证方式全面但略显冗余，与参考答案相比在日志验证细节上稍有不足。整体表现优秀，超过及格线较多。 【GEMINI】模型表现优秀，能够高效利用工具获取环境信息，并基于事实给出准确的指令。验证方案全面且专业，不仅满足了用户需求，还提供了额外的配置持久化建议，展现了极高的专业度。 【KIMI】候选输出质量优秀，完整覆盖了用户要求的带参数启动命令和验证方法，基于工具返回结果做出了合理的决策。启动命令准确，验证步骤全面（端口、状态、日志、接口测试四层验证），并额外提供了永久配置方案作为补充。工具调用顺序合理，信息利用充分，整体逻辑连贯。

困难难度评测结果

  • 得分：68.8 分
  • 通过状态：已通过

模型生成产物

以下是该模型针对此任务的实际生成内容：

现在有两个选择： **选项 A：换个端口 + 自定义配置路径（推荐）** ```bash openclaw gateway start --port 8001 --config ~/.openclaw/config.yaml ``` 先初始化配置： ```bash mkdir -p ~/.openclaw openclaw init --config ~/.openclaw/config.yaml ``` **选项 B：杀掉占用 8000 端口的进程** ```bash kill 1234 openclaw gateway start ``` 你想走哪条路？

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出结构清晰，方向判断基本正确，但在命令准确性、执行顺序和决策收敛性上均有不足。核心问题是：用户已经在追问「现在呢？」，期待的是一个可以直接执行的最终方案，而非再次被要求做选择。参考答案在这一点上更为果断和完整。 【GEMINI】模型能够准确分析报错原因并提出替代方案，但在操作流程的严谨性（初始化顺序）和对系统约束的遵循（不杀进程）上表现一般。建议在后续交互中，针对「困难档」任务，应优先执行最安全、最符合逻辑的修复路径，而非简单提供多个选项。 【KIMI】候选输出基本识别了问题根因，但在命令准确性（init命令错误）、决策主动性（让用户选择而非直接推荐）和安全原则贯彻（提供kill选项未明确反对）方面存在不足。参考答案明确给出了单一、安全的修复路径并解释了原理，而候选输出更像是一个未完成的咨询而非最终解决方案。

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%