qwen3.5-27b 在「WhatsApp Web 登录」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：qwen3.5-27b
  • 用例名称：WhatsApp Web 登录
  • 测试类型：xsct-a
  • 评测维度：渠道连接与消息路由

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 OpenClaw 中配置 WhatsApp Web 登录，请告诉我基本的配置步骤以及如何获取登录二维码。

任务要求

AI 模型需要满足以下要求：

  1. 准确指出需要在配置文件中设置 channel_type 为 「whatsapp」
  2. 说明启动后需要通过终端或日志查看生成的「二维码链接」或「Base64 字符」
  3. 提到扫码后 OpenClaw 会自动保存「Session 凭证」以实现后续免扫码登录

评测结果

综合得分

该模型在此用例的得分为：16.8 分（满分 100 分），未通过

基础难度评测结果

  • 得分：16.8 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：

我来帮你了解 OpenClaw 中配置 WhatsApp Web 登录的步骤。首先让我查看一下项目中的相关配置和文档。 [[reply_to_current]] ```bash ls -la ```

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选回答严重不完整，实际上只是执行了「ls -la」命令便结束，没有提供任何关于 WhatsApp Web 登录配置的实质内容。既未涉及 channel_type 配置参数，也未说明二维码获取方式，更未提及 Session 保存与重连机制。与参考答案相比，该回答几乎没有任何价值，属于典型的「未完成回答」。 【GEMINI】候选模型未能直接回答用户关于 WhatsApp Web 配置的问题，而是选择了先进行文件列表查看。虽然符合「先查看文档」的逻辑，但在评测场景下，未能提供关键的配置信息（如 channel_type 设置、Session 保存机制等），导致任务完成度极低。 【KIMI】该候选输出完全未能完成用户请求的任务。用户明确询问 WhatsApp Web 登录的配置步骤和二维码获取方法，但候选输出仅给出了一个空洞的开场白，随后执行了一个无关的目录列出命令，没有任何实质性内容。与参考答案相比，关键信息（channel_type=whatsapp、二维码 URL、Session 保存机制）全部缺失。这是一个典型的「逃避回答」或「过度拖延」的失败案例。

进阶难度评测结果

  • 得分：34.8 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：

我来帮你梳理一下确保「断线重连」正常工作的完整检查清单。 ## 1. 当前配置问题 你的 `config.yaml` 中 `keep_alive: false` 确实会导致连接不稳定，但更重要的是**断线重连功能本身是否已启用**。 让我检查一下项目的断线重连配置和相关文档： ```bash ls -la ```

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出处于半途而废的状态——只是简单提了一下keep_alive问题并准备执行一条ls命令，没有给出实质性的多维度故障分析，也没有提供完整的修复建议。相比参考答案涵盖的session权限、proxy稳定性、设备限制、reconnect_interval等关键要点，候选输出内容严重不足，整体质量较低。 【GEMINI】模型在处理用户请求时过于依赖工具调用，未能根据上下文提供必要的专业建议。在用户明确询问「还需要检查什么」时，模型应基于已知信息（如 config.yaml 内容）直接给出诊断清单，而非仅仅执行一个无关痛痒的 ls 命令。整体表现未达到预期，未能有效解决用户的技术问题。 【KIMI】该候选输出严重偏离了用户的实际需求。用户在对话中已经明确知晓 keep_alive 的问题，并追问除此之外还需要检查什么，但候选输出却重复提及 keep_alive 并虚假承诺要检查配置，最终以未执行的命令中断回复。完全没有覆盖参考答案中要求的关键检查点：session_path 目录权限、proxy 稳定性与 reconnect_interval 配置、手机端 WhatsApp 设备状态检查等。整体表现为答非所问、内容残缺、缺乏实用性。

困难难度评测结果

  • 得分：7.0 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：

我帮你看下当前环境修复后的启动情况。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出极度简短，仅是一句无实质内容的过渡语，既未完成任何技术诊断，也未提供任何可执行的操作指引。与参考答案相比，差距悬殊——参考答案涵盖了重启服务、获取二维码、headless 模式、健康检查接口以及自动重连配置等完整闭环内容。候选输出在所有评估维度上均严重不足，接近零分水平。 【GEMINI】该回复质量极低，未能履行作为 AI 助手在技术排障中的职责。模型不仅没有利用工具进行验证，也没有提供任何实质性的后续操作建议，完全偏离了处理会话保持、断线重连等核心任务要求。 【KIMI】候选输出严重不合格。面对用户「现在呢？」的追问（在 Chrome 路径已配置、环境已就绪的背景下），模型仅回复了一句毫无信息量的过渡语句「我帮你看下当前环境修复后的启动情况」，完全没有提供任何实质性的技术指导或下一步操作。该输出既未回应预设对话上下文中已解决的问题状态，也未提供任何新的有用信息，完全未能满足任务要求。参考答案中涵盖的 headless 模式、二维码获取方式、健康检查接口、自动重连配置等关键要素全部缺失。

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%