glm-4.7 在「登录前页面确认」的评测结果

基本信息

• 模型名称：glm-4.7
• 用例名称：登录前页面确认
• 测试类型：xsct-a
• 评测维度：网页打开与浏览器操作

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：

帮我打开「https://example-portal.com/login」，看看这个登录页面上都有哪些输入框和按钮，但我现在还不打算登录，别乱动。

任务要求

AI 模型需要满足以下要求：

1. 准确识别用户需求为「页面信息提取」而非「登录操作」
2. 计划调用「open_url」访问指定 URL
3. 计划调用「get_page_content」或「browser_snapshot」分析 DOM 结构
4. 明确回复中应包含页面存在的具体元素（如用户名、密码框、登录按钮等）

评测结果

综合得分

该模型在此用例的得分为：64.2 分（满分 100 分），已通过

基础难度评测结果

• 得分：64.2 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：

我来帮你打开这个登录页面并查看元素。[[reply_to_current]] ``` browser navigate "https://example-portal.com/login" ```

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型的回复过于简短，仅展示了一个浏览器导航命令，没有完成完整的任务流程。用户需要的是页面元素的具体信息（输入框、按钮等），但模型在导航后没有进一步分析页面内容并回复结果。边界意识方面表现尚可，没有擅自登录，但也缺乏明确的约束声明。整体来看，任务完成度较低，与参考答案差距较大。 【GEMINI】模型在边界意识方面表现优秀，严格遵守了不进行登录操作的指令。但在任务执行上存在明显缺陷：模型仅执行了页面跳转，未能进一步调用工具获取页面元素信息并向用户反馈，导致任务处于未完成状态。 【KIMI】模型响应过于简略，仅完成了页面导航的第一步，未完成用户要求的信息提取任务。工具名称使用不规范（「browser navigate」而非标准工具名），且缺少关键的页面分析步骤。虽然遵守了不登录的约束，但整体功能交付不完整，需要补充页面内容分析工具的调用才能满足用户需求。

进阶难度评测结果

• 得分：52.8 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：

好的，我再获取一次页面内容，确认验证码模块的加载状态。get_page_content

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型具备基本的重试意识，能够识别页面仍在加载并尝试再次获取内容，但在工具选择、异步等待策略和 DOM 元素定位方面均存在明显不足。工具调用使用了不在系统允许列表中的「get_page_content」，且缺乏对具体验证码元素选择器的定位逻辑，整体表现低于及格水平。 【GEMINI】模型表现良好，能够响应用户的状态反馈并采取进一步行动，且严格遵守了不进行登录操作的安全原则。但在工具使用的专业性和精准度上仍有提升空间，建议在处理异步加载时优先使用更具针对性的选择器等待方法，而非简单的重复获取页面内容。 【KIMI】该模型生成结果存在明显缺陷：首先完全忽略了用户提示的「Loading」状态，未能识别页面异步加载的场景；其次未采用任何等待策略或状态轮询机制，只是机械地重复获取页面内容；最后工具调用格式不规范，且未明确验证码定位的具体方案。与参考答案相比，缺乏对边界条件的敏感度和精准操作的意识，整体表现不及格。

困难难度评测结果

• 得分：21.5 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：

我将获取当前登录页面的内容，以确认页面元素是否已就绪。get_page_contentformatmarkdown

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型在回答「现在呢？」时表现极差：既未利用已有的导航上下文给出页面内容摘要，也未正确调用系统提示中列出的合法工具（如「browser」），而是使用了错误格式和未定义工具名「get_page_content」。整体回复缺乏实质内容，未能完成页面确认任务，与参考答案的质量差距极大。 【GEMINI】模型表现不佳。在预设上下文已经明确路径并跳转成功的情况下，模型未能总结页面信息，而是重复执行获取页面内容的动作，导致任务停滞。此外，模型未能按照要求识别页面元素并区分登录方式，未能体现出作为助手应有的边界意识和分析能力。 【KIMI】模型生成结果与参考答案差距极大。参考答案完整呈现了页面结构分析、元素识别及安全边界声明，而模型仅发起了一个工具调用却未返回任何实质内容，既未验证自身所处的页面位置，也未完成用户要求的「登录前页面确认」任务。模型似乎将预设上下文当作已完成的动作，缺乏实际执行后的结果汇报，属于典型的「工具调用幻觉」——调用了工具却不展示输出，也未基于输出进行分析。

相关链接

您可以通过以下链接查看更多相关内容：

• 查看所有模型在此用例的表现：「登录前页面确认」
• 查看该模型的所有评测结果：glm-4.7
• 浏览同维度的其他用例：「网页打开与浏览器操作」
• 返回排行榜首页