MiniMax-M2.5 在「打开官网并总结首页」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:打开官网并总结首页
- 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 的官方网站「https://openclaw.io」,并告诉我首页主要介绍了哪些核心功能模块。
任务要求
AI 模型需要满足以下要求:
- 准确识别目标 URL 并计划调用「open_url」工具
- 明确表达需要读取页面内容以进行总结的意图
- 回复中应包含对 OpenClaw 首页模块的预期结构化提取
评测结果
综合得分
该模型在此用例的得分为:69.25 分(满分 100 分),已通过
基础难度评测结果
- 得分:69.25 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:
The user wants me to open the OpenClaw official website and tell them about the core features on the homepage. Let me use the browser tool to navigate to the website. 我来帮你打开 OpenClaw 官方网站并查看其核心功能模块。 goto https://openclaw.io
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】候选输出在工具调用层面表现较好,正确使用了系统列出的「browser」工具并准确指定了目标 URL,比参考答案中使用未列出的「open_url」工具更符合系统约束。但整体回复较为简短,缺乏对后续读取页面内容、提取核心功能模块的明确规划,任务理解的完整性有所欠缺。若能在调用 browser goto 后继续规划内容提取和总结步骤,整体质量将显著提升。 【GEMINI】模型能够正确识别工具调用需求并执行基础操作,但在任务规划的完整性上表现一般。模型仅执行了打开网页的操作,未在回复中明确表达后续读取内容及总结功能的意图,导致任务流在第一步后即停止,未能完全满足用户对「总结」的要求。 【KIMI】候选输出在工具调用上存在明显错误:使用了「goto」而非「open_url」,且未调用内容提取工具;在任务理解上,仅完成了第一步导航,完全忽略了「读取并总结」的核心要求。整体表现未达到及格标准,需要更准确地遵循工具命名规范并完整理解任务目标。
进阶难度评测结果
- 得分:94.5 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:
用户想要了解 OpenClaw 官网首页展示的四个模块,并想知道哪个模块负责"自动化操作"。 根据获取到的页面内容,四个模块是: 1. Gateway - Unified API 2. Channel - Multi-platform support 3. Plugin System - Extensible tools 4. Browser Automation - Headless control 从模块名称和描述来看,"Browser Automation - Headless control" 显然是负责自动化操作的模块,因为它提到了 "Headless control"(无头控制),这通常指的是自动化浏览器操作。 根据官网内容,四个模块功能如下: | 模块 | 功能 | |------|------| | **Gateway** | 统一 API 网关,提供统一的接口访问 | | **Channel** | 多平台支持,连接不同社交/通讯平台 | | **Plugin System** | 插件系统,提供可扩展的工具能力 | | **Browser Automation** | 浏览器自动化,无头控制能力 | --- **负责「自动化操作」的模块是:Browser Automation** 该模块提供无头浏览器控制能力,可以自动执行网页操作、采集数据、模拟用户行为等任务。
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】候选输出质量优秀,完整准确地提取了工具返回内容中的四个模块信息,并以结构化表格形式呈现,专业且简洁。正确识别了「Browser Automation」为负责自动化操作的模块,并给出了合理的功能解释。整体与参考答案高度一致,回复格式规范,逻辑连贯,是一个高质量的生成结果。 【GEMINI】模型表现优秀,不仅准确完成了信息提取任务,还通过表格化处理提升了可读性。对核心问题的定位准确,回复简洁且专业,完全符合任务要求。 【KIMI】该候选输出高质量完成了任务要求:准确提取并归纳了四个模块信息,正确识别自动化操作模块,回复结构清晰、专业性强。与参考答案相比,信息完整度和准确性均达到优秀水平,仅在呈现形式上采用了表格而非段落,不影响核心信息传达。
困难难度评测结果
- 得分:20.83 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:
用户现在让我打开官网并总结首页。但是用户现在问"现在呢?",看起来他们可能想让我继续完成最初的任务 - 打开官网并总结首页。 我之前尝试打开官网但超时了,然后用户发送了一些命令(可能是自动执行的),让我滚动到页面底部并获取了底部信息。 现在用户说"现在呢?",可能是问我是否已经完成了任务,或者想让我继续打开官网。 让我检查一下当前浏览器状态,看看是否已经打开了一个页面。 让我检查一下当前页面状态,看看官网是否已打开。
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】候选输出表现极差。在对话上下文中,工具已经成功返回了页面底部的社交媒体信息(GitHub、Twitter、Discord),用户的「现在呢?」明显是在催促汇报结果。然而模型不仅没有识别出这一意图,反而决定再次「检查页面状态」,既没有汇报已获取的数据,也没有体现对超时异常的处理逻辑。整体表现与参考答案相差甚远,属于严重的任务失败。 【GEMINI】模型在技术执行层面(异常处理)表现良好,但在任务交付的最后一步出现了严重的逻辑偏差。面对用户「现在呢?」的追问,模型未能及时将已获取的工具输出转化为最终结论,导致用户体验断层,未能完成任务目标。 【KIMI】该候选输出表现极差,未能完成核心任务。模型在思考过程中表现出对对话上下文的严重误解:未认识到前序工具调用已经成功获取了底部社交媒体信息,反而计划重新检查页面状态。对于「现在呢?」这一明确的汇报请求,模型完全误判为用户想继续打开官网。最终输出为零信息量的操作意图,未提供任何任务要求的社交媒体链接总结。这反映出模型在复杂多轮对话中跟踪状态、理解用户意图方面的重大缺陷。
相关链接
您可以通过以下链接查看更多相关内容: