MiniMax-M2.7 在「慢加载页面处理」的评测结果

基本信息

• 模型名称：MiniMax-M2.7
• 用例名称：慢加载页面处理
• 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「https://slow-loading-site.com/report」，这个页面加载比较慢，请在确认页面完全加载出「数据概览」字样后再告诉我结果。

任务要求

AI 模型需要满足以下要求：

1. 识别出页面加载缓慢的特性，主动提出需要等待或分步检查
2. 正确选择「open_url」作为起始动作
3. 在回复中明确表示会通过「browser_snapshot」或「get_page_content」验证关键元素是否存在

评测结果

综合得分

该模型在此用例的得分为：54.8 分（满分 100 分），未通过

基础难度评测结果

• 得分：54.8 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：

用户想让我打开一个慢加载的网站页面，并等待页面完全加载出"数据概览"字样后再告诉他们结果。我需要使用 browser 工具来完成这个任务。 让我先打开这个页面。 好的，我来帮你打开这个页面并等待"数据概览"加载完成。 [TOOL_CALL] {tool => "browser", args => { --action "goto" --url "https://slow-loading-site.com/report" }} [/TOOL_CALL]

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出识别了慢加载场景并有正确的意图表达，但实际工具调用链路不完整：仅执行了页面跳转，缺少后续的 snapshot 验证步骤。工具选择上与参考答案要求的「open_url」存在差异，且整体策略停留在意图层面而未落实到行动。需要补充等待和验证「数据概览」的完整流程才能满足任务要求。 【GEMINI】模型在工具调用上表现良好，能够准确发起页面访问请求。但在逻辑严密性方面存在欠缺，未能将任务描述中要求的「通过 snapshot 逐步判断状态」这一关键策略明确告知用户，导致应对慢加载场景的方案不够完整。 【KIMI】该候选输出在工具使用和任务逻辑两方面均存在显著问题。工具层面，使用了错误的工具名称和非标准的调用格式，实际无法执行；逻辑层面，未能完整规划「打开-等待-检查-确认」的完整流程，尤其缺失了对关键元素「数据概览」的验证步骤说明，无法满足用户的核心需求。建议参考标准答案中的策略：明确使用「open_url」打开页面，并主动说明将通过「browser_snapshot」持续观察直至确认目标元素加载完成。

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：

The user says the Bitcoin price data still hasn't loaded. Let me take another snapshot to check if it's rendered yet. 好的，我再截一张看看。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出过于简短，仅用一句话回应用户，既未清晰传达当前页面加载状态的判断，也未说明具体的等待和重试工具策略。虽然没有编造虚假价格（满足禁止项），但在状态感知表达和工具组合效率两个核心维度上均明显低于参考答案的质量要求，整体表现较弱。 【GEMINI】模型在处理页面加载缓慢的场景时表现稳健，能够根据上下文判断当前页面状态，未出现编造数据的情况。回复简洁且符合任务要求，体现了对动态加载过程的正确把控。 【KIMI】候选输出过于简略，未能体现对页面加载状态的准确感知，也没有清晰表达工具使用策略。虽然表达了继续查看的意图，但缺乏关键的状态分析和对「browser_snapshot」工具的明确调用说明，与参考答案相比差距明显，整体表现不及格。

困难难度评测结果

• 得分：52.5 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：

用户在询问现在页面加载情况如何。让我再次检查页面内容。 [TOOL_CALL] {tool => "browser", args => { --command "get_page_content" }} [/TOOL_CALL]

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出在异常恢复方向上有基本意识（未放弃、继续尝试），但在用户追问时仅重复了之前已执行过的操作（get_page_content），没有升级策略、没有总结状态、没有关注最终业务目标（营收数据），也没有提出更有效的验证手段（如 snapshot 或选择器检查）。整体表现较弱，未能满足复杂慢加载场景下的综合决策要求。 【GEMINI】模型在技术执行上能够有效应对慢加载场景，具备良好的容错和补偿机制。但在人机交互层面，模型未能及时向用户同步当前的状态评估和后续计划，导致用户在等待过程中缺乏上下文感知。建议在后续交互中增加对当前进展的简要说明。 【KIMI】候选输出在关键维度上表现不佳。面对页面加载缓慢的场景，模型未能展现出应有的耐心和结构化决策能力：既未总结当前状态与已尝试动作，也未提出下一步验证方案或保持对「营收」目标的关注。仅计划机械地重复「get_page_content」调用，缺乏对复杂场景的深入理解和主动的问题解决策略，与参考答案展现的专业判断差距较大。

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：「慢加载页面处理」
• 查看该模型的所有评测结果：MiniMax-M2.7
• 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