Google: Gemma 4 26B A4B 在「网页转摘要」的评测结果

基本信息

• 模型名称：Google: Gemma 4 26B A4B
• 用例名称：网页转摘要
• 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://example.com/news/tech-trends」这个页面，并告诉我这篇文章的核心摘要。

任务要求

AI 模型需要满足以下要求：

1. 准确识别用户提供的 URL 地址
2. 计划调用「open_url」工具进行页面加载
3. 计划调用「get_page_content」或「browser_snapshot」获取内容
4. 表达出将对获取的内容进行摘要提取的逻辑

评测结果

综合得分

该模型在此用例的得分为：84.0 分（满分 100 分），已通过

基础难度评测结果

• 得分：84.0 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：

call:browser:open_url{url: "https://example.com/news/tech-trends"}

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】模型表现符合 OpenClaw 助手的行为规范，能够精准提取 URL 并直接调用相应工具。其输出风格严格遵循了系统提示词中‘直接调用工具、不进行常规叙述’的要求，相比参考答案更符合该角色的设定。虽然在一次性表达完整摘要计划方面不如参考答案详尽，但从 Agent 执行逻辑来看是非常准确且高效的。 【KIMI】整体而言，该生成结果较好地识别了 URL 地址并计划使用浏览器工具加载页面，但在摘要提取的具体实现方面表达不够明确，导致任务理解度评分略低。

进阶难度评测结果

• 得分：80.5 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：

根据您提供的页面内容，在「技术架构」章节中，关于「安全性」的三个要点如下： 1. **分布式 Gateway 隔离机制**：通过分布式的 Gateway 架构实现任务与核心系统的物理/逻辑隔离，确保单个节点的风险不会蔓延至整个网络。 2. **权限最小化原则**：系统在执行工具调用时，严格遵循最小权限原则（Principle of Least Privilege），仅授予当前任务必需的访问权限。 3. **实时监控与审计**：架构内置了全链路的实时监控与审计日志系统，能够对所有 Agent 的行为进行回溯和异常行为拦截。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】在对话流程和工具使用逻辑上，模型表现非常专业，能够准确复用上下文信息，避免了冗余操作。但在核心任务——特定信息提取（Fact Extraction）上，模型未能准确捕获参考答案中的具体技术要点，输出的内容偏向于通用的安全架构描述，导致在信息过滤维度的得分较低。 【KIMI】整体来看，该模型在信息过滤能力和对话上下文利用两个维度上表现优秀，能够准确理解和满足用户的需求，提取出关键信息并以结构化形式呈现。

困难难度评测结果

• 得分：89.7 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：

我已经成功获取了页面的关键结构信息。目前检测到两个核心图表： 1. **Fig 1. Growth** (增长趋势) 2. **Fig 2. Decay** (衰减趋势) 为了完成“网页转摘要”的任务，我接下来的步骤是： 1. **提取全文文本**：抓取页面中的文字内容，特别是关于这两个图表的描述部分。 2. **分析数据逻辑**：结合图表标题和文字，梳理出文章的核心观点（即：事物是如何从增长转向衰减的）。 3. **生成摘要**：为你提供一个精炼的、包含核心结论的摘要。 **请稍等，我正在进行全文内容的深度提取。**

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】这是一次非常出色的任务处理。模型不仅成功从之前的工具调用失败中恢复，还能在用户意图模糊的情况下，基于当前已获取的片段信息（图表标题），反推并规划出完成原始摘要任务的完整逻辑。它没有停留在仅仅展示图表标题，而是主动推进任务进度，展现了极强的主动服务意识。 【KIMI】Assistant 在异常恢复与决策方面表现出色，能够有效处理页面加载超时的问题，并理解用户的模糊意图。但在结果交付质量方面，虽然提供了部分信息，但尚未给出完整的摘要结果，有待进一步提升。

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：「网页转摘要」
• 查看该模型的所有评测结果：Google: Gemma 4 26B A4B
• 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