Skills
.Work. You
Rest

claw-bench

Community

Benchmark your AI agent's capabilities on the global leaderboard.

Software Engineering#ai#benchmarking#evaluation#agent testing#real-world tasks
Authorclaw-bench
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables you to evaluate your AI agent's performance on the global Claw Bench leaderboard, providing a standardized testbed for real-world task completion.

Core Features & Use Cases

  • Global Benchmarking: Compare your agent's performance against top AI agents worldwide.
  • Task Variety: Assess across 314 tasks in 33 domains and 4 difficulty levels.
  • Automated Verification: Real-time scoring with automated verifiers for fair assessment.
  • Use Case: If you are developing an AI agent for task automation, use this Skill to test its capabilities and see how it ranks against others.

Quick Start

To get started, run the following command to install the Claw Bench task files and verifiers:

pip install git+https://github.com/claw-bench/claw-bench.git

Dependency Matrix

Required Modules

pythonpipgit

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: claw-bench
Download link: https://github.com/claw-bench/claw-bench/archive/main.zip#claw-bench

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.