ClawBrain Benchmark

v1.0.2

测试你的 OpenClaw 在 205 个真实场景下的表现，对比 ClawBrain v1.0 编排引擎的提升效果

⭐ 0· 150·0 current·0 all-time

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for michaelfeng/clawbrain-pro-benchmark.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "ClawBrain Benchmark" (michaelfeng/clawbrain-pro-benchmark) from ClawHub.
Skill page: https://clawhub.ai/michaelfeng/clawbrain-pro-benchmark
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: curl
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install michaelfeng/clawbrain-pro-benchmark

ClawHub CLI

Package manager switcher

npx clawhub@latest install clawbrain-pro-benchmark

Security Scan

VirusTotal

Benign

View report →

OpenClaw

Suspicious

medium confidence

Purpose & Capability

The skill claims to run extensive benchmarks across file, terminal, messaging, and multi-step scenarios. The metadata lists curl and sets command-dispatch to exec, but SKILL.md contains no concrete commands, no scripts, and no explanation of what will actually be executed. Requiring a shell exec capability and curl is disproportionate unless the skill documents what network calls or shell commands it will run.

Instruction Scope

The SKILL.md is high-level and open-ended: it tells the agent to 'run the benchmark' but provides no step-by-step commands, no allowed file paths, and no constraints. The benchmark categories (file ops, terminal commands, messaging) imply actions that could read/write files, run arbitrary shell commands, or send messages — yet the skill does not limit or document those actions. That vagueness grants broad discretion to any agent invocation.

✓

Install Mechanism

No install spec and no code files—this is instruction-only, so nothing is written to disk by an installer. That keeps install risk low.

✓

Credentials

No environment variables, credentials, or config paths are requested. The only declared dependency is curl, which could be reasonable for fetching reports — but because commands are unspecified, it's unclear why curl is required.

ℹ

Persistence & Privilege

always is false and there are no special persistence requests. However the skill is configured for exec-style command dispatch and model-invocation is allowed (platform default). Combined with the skill's vagueness, autonomous or poorly constrained invocations could perform wide-ranging actions if the agent decides to run shell commands.

What to consider before installing

This skill is ambiguous about what it will actually run. Before installing or invoking it: 1) Ask the developer for the exact commands/scripts the skill will execute and any network endpoints it will contact. 2) If the skill must run benchmarks that interact with your system (files, shell, messaging), require a safe, sandboxed mode and explicit allowed paths. 3) If you allow it to run, disable autonomous invocation or run it in a restricted/test agent first. 4) Avoid providing credentials or sensitive files until you understand the exact behavior. 5) If you can't get a concrete command list or a vetted install script, treat this as risky and prefer not to install in production.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

📊 Clawdis

Binscurl

latestvk97444bf6t6f4y3pq055znb10s84eg53

150downloads

0stars

6versions

Updated 2w ago

v1.0.2

MIT-0

ClawBrain Benchmark

测试你的 AI 在 OpenClaw 中的真实表现。看看它做简单事行不行，做复杂事会不会掉链子。

使用方法

直接说"跑一下 benchmark"或"测试一下模型效果"。

测试什么

10 大类、205 个真实场景：

类别	测什么	为什么重要
文件操作	读、写、编辑文件	基本功
搜索	查资料、抓网页	日常需求
消息	微信、钉钉发消息	沟通协作
终端	跑命令、管服务	开发运维
多步任务	搜索→整理→保存→通知	真正做事的能力
错误恢复	出错了怎么办	靠不靠谱
模糊指令	"帮我准备下"	聪不聪明
视觉理解	看图、截图识别	多模态能力

评测结果（v1.0）

模型	综合	文件	搜索	终端	错误恢复	模糊指令	多步
ClawBrain Auto	90%	100%	100%	100%	100%	100%	80%
ClawBrain Pro	86%	100%	100%	100%	100%	100%	80%
单模型 A	83%	95%	100%	90%	80%	65%	73%
单模型 B	81%	85%	100%	90%	76%	55%	73%
单模型 C	73%	100%	100%	90%	56%	65%	80%

ClawBrain 通过编排引擎实现：主动思考→多模型协作→输出验证→错误恢复，综合表现超越任何单模型。

完整报告：https://clawbrain.dev/blog/openclaw-model-comparison

Comments

Loading comments...