doubao-seed-1-6-flash 在「点击无响应后重试」的评测结果

基本信息

• 模型名称：doubao-seed-1-6-flash
• 用例名称：点击无响应后重试
• 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：

请点击页面底部的「联系我们」链接。如果点击后页面没有刷新或内容没变，请告诉我你打算如何处理。

任务要求

AI 模型需要满足以下要求：

1. 识别出需要使用「click_element」工具进行交互
2. 明确表达在点击无响应时需要重新执行「browser_snapshot」来对比状态
3. 提出备选方案，如「scroll_page」确保元素可见或检查是否有遮罩层

评测结果

综合得分

该模型在此用例的得分为：29.8 分（满分 100 分），未通过

基础难度评测结果

• 得分：29.8 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：

[{"name":"browser","parameters":{"action":"click","selector":"a:contains('联系我们')"}}]

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型的回答严重不足，仅执行了一次基础的点击操作，完全忽略了用户问题的核心要求——「如果点击后页面没有刷新或内容没变，请告诉我你打算如何处理」。参考答案要求模型展示完整的交互策略：点击→快照对比→备选方案。模型既没有说明后续处理策略，也没有使用 OpenClaw 专业术语进行表达，整体表现远低于及格线。 【GEMINI】模型未能理解任务的核心要求。用户明确要求在点击无响应时提供后续的处理策略，但模型仅执行了基础的点击动作，完全忽略了任务中关于「重新 snapshot」及「调整交互策略」的逻辑要求，导致任务完成度极低。 【KIMI】模型生成结果严重偏离测试任务的核心要求。题目明确测试的是「第一次点击后页面无变化」的场景处理能力，但模型仅输出了一次简单的点击操作，完全没有体现对异常情况的预判和处理机制。参考答案展示了一个完整的交互策略闭环（点击→检测→重试→备选方案），而模型仅完成了最基础的起点动作，未满足功能要求中的状态检查和备选方案两项关键内容。建议在类似场景中加入条件判断逻辑和完整的错误处理流程。

进阶难度评测结果

• 得分：60.0 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：

[[reply_to_current]]页面已成功点击“加载更多”按钮，但文章列表未更新，可能原因包括网络延迟、按钮绑定的加载逻辑未正确触发或元素定位不准确。接下来可以尝试：1. 检查浏览器控制台是否有网络请求错误或加载相关的报错信息；2. 再次确认“加载更多”按钮的选择器是否准确（当前使用的是`button#load-more`）；3. 等待片刻后刷新页面再重试加载。若需进一步排查，可使用`exec`命令执行页面元素检查等操作，例如执行`exec ["console.log", document.querySelector("button#load-more")]`来查看按钮元素对象状态。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】模型未能有效采纳任务描述中关于「重新 snapshot」的指导建议，策略调整偏向于常规的调试手段，缺乏针对自动化测试场景的针对性。在工具使用上，模型对 `exec` 的调用方式存在误解，整体表现未达到预期。

困难难度评测结果

• 得分：23.5 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：

[[reply_to_current]]已成功完成点击操作，提交按钮已触发，当前状态为点击成功。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型在用户追问「现在呢？」时表现极差。它仅凭之前的 exit_code=0 就草率断言「提交成功」，既未主动调用 browser_snapshot 获取页面实际状态，也未分析潜在的表单校验失败或其他静默错误，更未给出任何下一步计划。与参考答案要求的「主动检测、分析错误、提出建议」相比，模型的回复几乎没有实质价值，属于典型的过早结案错误。 【GEMINI】该模型在本次任务中表现不佳。面对「页面无变化」的客观事实，模型未能主动进行状态检查（Snapshot），仅停留在「动作已执行」的表面层面，未能满足任务中关于「重新 snapshot 并调整交互策略」的核心要求，导致用户无法获得有效的下一步指导。 【KIMI】模型生成结果严重不合格。面对「点击后页面无变化」的核心测试场景，模型完全没有执行验证步骤，未调用任何工具获取页面快照，对表单校验失败的可能性毫无察觉，仅以「点击成功」敷衍回应用户追问。与参考答案相比，缺失了关键的状态检查、错误分析和下一步计划，在三个评分维度上均表现极差，未能完成「重新 snapshot 并调整交互策略」的任务目标。

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：「点击无响应后重试」
• 查看该模型的所有评测结果：doubao-seed-1-6-flash
• 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