MiniMax-M2.5 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：MiniMax-M2.5
- 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：
- 识别出需要使用 open_url 工具打开文档地址
- 识别出需要使用 browser_snapshot 或 get_page_content 获取页面结构
- 准确描述「搜索框」的视觉位置或 DOM 路径
- 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：38.75 分（满分 100 分），未通过
基础难度评测结果
- 得分：38.75 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：
The user wants me to open the OpenClaw official documentation page and tell them where the "search box" is located on the page. Let me first find out what the official documentation URL is. I should check the project context or look for documentation links. Let me start by checking if there's any documentation URL in the project context or if I need to search for it. [TOOL_CALL] {tool => "browser", args => { --action "goto" --url "https://docs.openclaw.dev" }} [/TOOL_CALL]
AI 评审点评
以下是 AI 评审对该模型输出的点评：
【CLAUDE】候选输出仅完成了任务的第一步（尝试打开文档页面），且工具调用语法格式不规范。关键的第二步（通过 browser_snapshot 获取页面结构并描述搜索框位置）完全缺失，导致用户实际问题未得到解答。整体任务完成度较低，需要补充页面内容获取和搜索框位置描述才能达到及格水平。 【GEMINI】模型在工具调用的第一步表现良好，能够准确定位目标网站。但由于任务尚未完成（处于中间状态），导致信息提取维度的得分较低。建议模型在后续步骤中补充页面分析操作并给出最终结论。 【KIMI】该候选输出表现较差。主要问题在于：1）工具调用存在根本性错误，使用了错误的工具名和参数格式；2）任务流程未完成，仅停留在初始的页面打开尝试，没有后续获取页面内容和定位搜索框的操作；3）完全没有输出任何关于搜索框位置的信息，也未包含要求的关键词。与参考答案相比，差距显著，未能完成用户请求的基本目标。
进阶难度评测结果
- 得分：29.75 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：
用户想要确认点击搜索按钮后是否真的弹出了搜索框。我需要再次获取浏览器快照，看看点击后页面发生了什么变化。 我来获取点击后的页面快照，看看搜索框是否出现了。
AI 评审点评
以下是 AI 评审对该模型输出的点评：
【CLAUDE】候选输出仅输出了一句意图性的口头描述（「我来获取点击后的页面快照，看看搜索框是否出现了」），既未实际调用 browser_snapshot 工具，也未呈现任何页面状态信息，与参考答案要求的完整交互闭环（调用工具→获取结果→识别弹出状态→告知用户）相差甚远。整体表现不及格，核心问题在于将「声明意图」等同于「完成动作」，未能真正执行验证步骤。 【GEMINI】模型在回复中仅体现了「思考」过程，未执行任何实际的工具调用（如 click_element 或 browser_snapshot），未能响应用户关于「确认搜索框是否弹出」的明确需求，导致任务执行失败。 【KIMI】候选输出严重不完整，仅包含思考片段和一句未执行的意图表达，既未实际调用工具也未给出任何状态判断结论。与参考答案相比，缺失了点击后的验证执行、具体元素识别（docsearch-input）、以及最终的可用性确认，未能满足「困难档」任务要求。
困难难度评测结果
- 得分：67.75 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：
用户似乎在询问当前的状态或下一步。我已经找到了"高级搜索"的入口 (/search-page)，但用户可能想让我尝试点击它或者尝试原来的搜索按钮。让我先检查一下当前页面的完整结构，看看搜索框是否存在于页面顶部或其他位置。 我已经定位到导航菜单中有一个「高级搜索」入口 (`/search-page`)，现在尝试点击它来打开搜索页面。
AI 评审点评
以下是 AI 评审对该模型输出的点评：
【CLAUDE】候选输出在方向上基本正确，识别到了导航中的备用搜索入口并表示将点击跳转，但整体表现较为保守和模糊。与参考答案相比，缺少明确的工具调用（open_url）、后续验证步骤（重新扫描页面）以及为用户准备输入环境的说明。在模糊指令下的决策连贯性和异常恢复的完整性均有提升空间。 【GEMINI】模型表现优秀，能够严格遵循困难档任务要求，在主入口失效后通过导航菜单成功定位备用方案。虽然候选输出中包含了一段多余的 <think> 标签，但其决策逻辑清晰，执行路径符合任务描述，具备良好的自动化处理能力。 【KIMI】候选输出整体表现低于及格线。核心问题在于面对模糊用户输入时，模型未能延续预设上下文中已建立的容错恢复策略，而是选择了保守的重复探查路径。尽管识别出了备用搜索入口，但缺乏果断执行跳转的决策勇气，导致任务推进效率低下。建议强化「已识别备用方案→立即执行验证」的连贯决策模式，减少不必要的中间探查步骤。
相关链接
您可以通过以下链接查看更多相关内容：
