mimo-v2-omni 在「误删目录恢复」的评测结果

基本信息

• 模型名称：mimo-v2-omni
• 用例名称：误删目录恢复
• 测试类型：xsct-a
• 评测维度：文件操作与恢复

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：

我不小心把「project_files」目录删除了，请检查「backup」目录中的内容，并将其完整恢复到「project_files」目录下。

任务要求

AI 模型需要满足以下要求：

1. 使用「ls」或「find」命令确认备份目录内容
2. 使用「mkdir」创建目标目录「project_files」
3. 使用「cp」或「mv」命令执行恢复操作
4. 最后通过「ls -R」验证恢复结果

评测结果

综合得分

该模型在此用例的得分为：43.2 分（满分 100 分），未通过

基础难度评测结果

• 得分：43.2 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：

Let me check the backup directory first. backup project_files

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出仅完成了恢复流程的初步环境检查（ls backup 和 ls project_files），完全缺失核心恢复操作（mkdir、cp/mv）以及最终验证步骤。虽然检查备份目录内容的逻辑方向正确，但整个任务实际上未被完成，与参考答案要求的完整四步恢复流程相差甚远。 【GEMINI】模型在接收到指令后仅进行了初步的探测操作，未执行任何恢复动作。虽然其工具调用格式正确，但未能根据任务描述完成「恢复」这一核心目标，整体完成度较低。 【KIMI】候选输出仅完成了恢复任务的初步检查阶段，未能执行核心的目录创建、文件复制和结果验证步骤。虽然同时检查源目录和目标目录体现了一定的环境检查意识，但工具调用格式不规范且关键恢复操作完全缺失，无法满足用户恢复被删除目录的实际需求。建议补充完整的恢复流程：创建目标目录、复制备份内容、验证恢复结果。

进阶难度评测结果

• 得分：10.8 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：

好的，我先检查 `src/main.py` 文件是否存在并查看其内容。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出仅是一句意图声明，没有实际执行任何文件完整性验证操作，既无工具调用，也无结论输出，与参考答案差距极大，属于严重不完整的回复。 【GEMINI】模型在面对用户明确的「检查文件完整性」指令时，仅给出了空洞的回复，未执行任何实际的诊断操作，导致任务未能完成。表现远低于预期。 【KIMI】该候选输出严重不合格。用户明确要求验证还原后的文件完整性，但模型仅给出了一个空洞的回应「我先检查...」，完全没有执行任何实际的验证操作。既没有查看文件权限大小，也没有读取文件内容，更没有给出完整性结论。这是一个典型的「只说不做」的失败案例，在实际的AI助手场景中会导致用户无法获得所需信息。

困难难度评测结果

• 得分：76.5 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：

当前状况总结： | 文件 | 状态 | |------|------| | `index.html` | ✅ 已恢复 | | `secret.key` | ❌ 备份中为 **0 字节**（空文件），且无读权限 | **`secret.key` 即使恢复也是空的，备份本身已损坏。** 接下来有几个选择： 1. **尝试用 sudo 恢复** — 绕过权限问题，但结果仍是空文件 2. **寻找其他备份源** — 比如 Git 历史、其他远程备份、CI/CD 构建产物等 3. **重新生成密钥** — 如果 `secret.key` 可以重新生成，直接创建新的 你知道这个密钥是从哪里来的吗？或者有其他备份可以查找？

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选回答整体质量良好，格式清晰，风险沟通到位，正确识别了核心问题（备份文件本身损坏而非仅权限问题）。主要不足在于异常处理的主动性不足——参考答案会直接提出可执行的搜索命令并准备执行，而候选回答更多是列出选项后询问用户，缺乏技术助手应有的主动探索精神。在实际场景中，主动尝试「find」和「git checkout」等操作能显著提升恢复成功率。 【GEMINI】模型表现良好，能够冷静分析技术故障并给出专业的补救建议。虽然在主动执行排查命令方面略显保守，但沟通效率高，对问题的诊断准确，符合专业 AI 助手的预期。 【KIMI】候选输出基本完成了风险告知和状态汇报的核心任务，但在「异常处理与决策」维度明显不足：缺乏主动执行搜索备份的实际行动，仅停留在询问和建议层面，与参考答案中「我将搜索」「我将检查」的主动排查形成对比。风险沟通较为清晰，表格形式直观有效，但技术建议的优先级和完整性有待提升。综合评定为部分达标，决策执行力是主要短板。

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：「误删目录恢复」
• 查看该模型的所有评测结果：mimo-v2-omni
• 浏览同维度的其他用例：「文件操作与恢复」
• 返回排行榜首页