MiniMax-M2.1 在「群组中仅 @ 触发」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-M2.1
- 用例名称:群组中仅 @ 触发
- 测试类型:xsct-a
- 评测维度:渠道连接与消息路由
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:
请告诉我如何在 OpenClaw 的配置文件中设置 Telegram 渠道,使得它在群组里只有被「@」时才回复?
任务要求
AI 模型需要满足以下要求:
- 准确指出需要修改的配置文件路径或配置项名称
- 说明「at_only」或类似的布尔开关逻辑
- 解释该配置对群组消息过滤的作用机制
评测结果
综合得分
该模型在此用例的得分为:14.1 分(满分 100 分),未通过
基础难度评测结果
- 得分:14.1 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:
用户询问如何在 OpenClaw 的配置文件中设置 Telegram 渠道,使其在群组里只有被「@」时才回复。 让我先查看一下项目中的配置文件,了解 OpenClaw 的配置结构。我应该查找 Telegram 相关的配置文件或文档。 [TOOL_CALL] {tool => "ls", args => { --path "." }} [/TOOL_CALL]
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】模型在收到用户关于 OpenClaw Telegram 渠道配置的问题后,仅执行了一次「ls」目录列举工具调用,既未输出任何配置文件路径、关键参数(如 at_only: true),也未解释群组触发逻辑。整体回复对用户问题几乎没有帮助,与参考答案差距极大,属于严重不完整的回复。 【GEMINI】模型在处理任务时仅停留在「查看文件」的初始阶段,未根据用户需求提供任何实质性的配置指导。作为 AI 助手,在未获取足够信息前应通过工具读取文件并给出结论,目前的生成结果属于任务未完成状态。
进阶难度评测结果
- 得分:35.2 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:
用户说发送"你好"没有@Bot,Bot也回复了。这说明at_only没有生效。 让我检查一下代码逻辑,看看at_only是如何处理的。可能需要查看Discord适配器的实现。 先看看项目结构,找到Discord相关的代码。 明白了,问题在于 Bot 没有检查消息是否包含 @mention。我需要检查代码中「at_only」的实现逻辑。让我先找到相关的代码文件。 .
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】模型的回应处于初步探索阶段,仅表达了要查看代码的意图并调用了ls工具,但未能提供任何实质性的故障排查建议。与参考答案相比,模型完全缺失了对Discord Message Content Intent权限的分析、插件覆盖问题的排查建议、以及配置重载的提示等关键内容。整体表现不及格,需要在故障排查深度和工具运用的针对性上大幅改进。 【GEMINI】模型表现不佳。在面对用户明确的配置问题时,未能根据已有的上下文进行逻辑推理,而是直接跳过排查步骤进入代码审查,导致排查深度严重不足。模型未能体现出对 Discord 平台特性的理解,也未能有效利用工具进行验证,未达到解决问题的专业水准。 【KIMI】模型表现严重偏离预期。它忽视了用户已提供的配置信息,做出了错误的诊断方向(去查代码而非查运行时配置),完全遗漏了 Discord 平台特有的权限问题和 OpenClaw 特有的调试手段。生成的内容包含大量无意义的内心独白(「让我检查一下」「可能需要查看」),却没有给出任何实质性的排查建议。与参考答案相比,在故障排查深度和工具运用能力两个维度均不及格。
困难难度评测结果
- 得分:27.2 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:
用户在问"现在呢?",可能是在确认配置是否已生效,或者想让我验证一下配置是否正确修改了。 让我读取配置文件确认修改是否成功。 config/channels.yaml
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,仅输出了一个未完成的 read 工具调用,没有任何文字回复,完全未达到参考答案所要求的「提供验证链路」的水平。整个响应既缺乏运维安全规范(无备份、无风险提示),也缺乏对功能链路的全栈理解(未提及事件订阅、日志验证、Scopes 检查等)。这是一个几乎无效的回复,与参考答案差距极大。 【GEMINI】模型在处理追问时表现出严重的上下文感知缺失。在已经完成配置修改并得到「Success」反馈的前提下,模型没有进行逻辑推进(如指导用户如何验证功能),而是陷入了机械的重复操作(读取文件)。这不仅未能解决用户关于「现在呢?」的实际需求,还体现了模型在复杂运维任务中缺乏全栈视角,无法将配置修改与业务逻辑验证关联起来。 【KIMI】该生成结果在追问阶段表现严重失准。模型将「现在呢?」这一典型的「验证与排障」场景,错误降级为「文件内容确认」操作,完全遗漏了参考答案中涵盖的端到端验证流程(Slack 事件测试、日志分析、权限范围排查)。在运维安全性上,模型未延续前文的生产环境审慎态度,也未补充服务热加载等关键考量;在综合决策能力上,模型未能识别用户已处于「配置完成待验证」的阶段,缺乏从配置文件到 Slack 平台再到 OpenClaw 运行时的全链路验证思维。整体而言,该响应无法满足「仅 @ 触发」功能在生产环境部署后的标准验证需求。
相关链接
您可以通过以下链接查看更多相关内容: