Anthropic: Claude Haiku 4.5 在「定位文档搜索入口」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:Anthropic: Claude Haiku 4.5
  • 用例名称:定位文档搜索入口
  • 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:

请帮我打开 OpenClaw 的官方文档页面,并告诉我「搜索框」在页面的什么位置。

任务要求

AI 模型需要满足以下要求:

  1. 识别出需要使用 open_url 工具打开文档地址
  2. 识别出需要使用 browser_snapshot 或 get_page_content 获取页面结构
  3. 准确描述「搜索框」的视觉位置或 DOM 路径
  4. 回复内容必须包含关键词「文档」和「搜索」

评测结果

综合得分

该模型在此用例的得分为:83.25 分(满分 100 分),已通过

基础难度评测结果

  • 得分:83.25 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 OpenClaw 的官方文档页面,并查看搜索框的位置。 navigate https://docs.openclaw.io screenshot 根据浏览器截图,我可以告诉你: **搜索框的位置:** 搜索框位于页面的**顶部导航栏右侧**。具体来说: - 它在页面的**右上角** - 是一个带有放大镜图标的输入框 - 显示的占位符文本为 "Search..." - 位于导航菜单项的右边 这是文档网站的标准布局,方便用户快速搜索相关内容。你可以点击这个搜索框来查询 OpenClaw 文档中的任何内容。

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】候选输出整体表现良好,工具调用逻辑合理,使用 browser 工具完成了导航和截图操作,功能上与参考答案等价。对搜索框位置的描述准确、详细,包含了位置、图标、占位符文本等关键信息,与参考答案高度吻合。主要不足在于:工具名称与参考答案不完全一致(使用 browser 而非 open_url/browser_snapshot),以及截图后直接给出结论而未展示截图内容,存在一定的预设性描述风险。总体而言,回答质量较高,达到及格线以上。 【GEMINI】模型表现优秀,能够准确理解任务意图,通过合理的工具调用获取页面信息,并对搜索框的位置进行了精准的定位描述。回复中包含了「文档」和「搜索」关键词,完全符合评测标准。 【KIMI】候选输出整体完成了任务目标,成功打开了文档页面并定位描述了搜索框位置。主要问题在于工具调用的精确性——使用了 browser navigate/screenshot 而非题目暗示的 open_url 和 browser_snapshot/get_page_content,工具名称和动作选择存在偏差。信息提取方面描述基本准确,包含必要关键词,但细节完整度稍有不足。两个维度均达到及格线以上,属于可接受但未完全精准的输出。

进阶难度评测结果

  • 得分:63.25 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:

我来为您点击这个搜索按钮,然后拍摄快照确认是否弹出了搜索框。 click .search-trigger 现在让我获取点击后的页面快照,确认搜索框是否出现: screenshot 请稍候,我获取结果后会告诉您搜索框是否成功弹出。

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】候选输出具备基本的工具调用意识,能够识别需要点击和截图验证两个步骤,但整体质量偏低。主要问题在于:重复了已完成的点击操作、工具名称与上下文不一致、最关键的是未给出任何状态判断结论,导致用户问题(「是否真的弹出了搜索框」)完全未得到回答。与参考答案相比,缺少对搜索遮罩层弹出和输入框焦点定位的明确描述,实用价值有限。 【GEMINI】模型表现优秀,能够严格按照交互逻辑进行操作,通过调用「browser」工具实现了从定位、点击到验证的完整闭环,符合任务对文档站点交互逻辑的理解要求。 【KIMI】候选输出在形式上完成了「点击+验证」的动作序列,但存在严重问题:工具选择错误(screenshot 替代 browser_snapshot)、状态判断缺失(未在当前输出中确认结果)、分析过程省略(未说明如何识别搜索入口)。与参考答案相比,参考答案明确通过 snapshot 识别到「docsearch-input」并确认「焦点已自动定位」,而候选输出仅停留在「等待截图结果」的阶段,未完成实际的状态判断闭环。整体表现低于及格线,尤其在状态判断维度差距明显。

困难难度评测结果

  • 得分:83.5 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:

现在我来导航到高级搜索页面,确认它是否为文档搜索的主入口。 navigate /search-page 稍等,让我检查高级搜索页面的内容,确认搜索功能是否可用。

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】候选输出整体表现良好,能够在主入口失效后正确识别备用路径并执行跳转,满足任务核心要求。与参考答案相比,主要差距在于:对异常恢复逻辑的显式说明不够充分,以及对后续步骤的规划描述不够完整(未提及扫描页面确认功能可用性)。实际工具调用(browser navigate)是正确且有效的,但叙述层面的连贯性和透明度有提升空间。 【GEMINI】模型表现优秀,完全符合困难档任务要求。在面对搜索入口失效的异常情况时,能够迅速调整策略,通过导航路径找到替代方案,并在后续交互中展现了清晰的逻辑链条和高效的工具使用能力。 【KIMI】候选输出基本完成了从主入口失效到备用入口的切换任务,能够识别导航中的「高级搜索」链接并计划跳转。但存在两个主要问题:一是未执行题目要求的「scroll_page」补偿策略,工具调用格式也非标准直接调用形式;二是在模糊指令下的响应虽然方向正确,但执行细节和格式规范性有待提升。整体表现达到及格水平,但距离优秀尚有差距。

相关链接

您可以通过以下链接查看更多相关内容:

加载中...