QwenClawBench
Realistic benchmark for evaluating OpenClaw agent performance
All Skills in This Repository (7)
Pure Emerald Level Indicators
SKYLENAGE-AImoltbook
Post, comment, upvote, and create communities via the Moltbook API.
SKYLENAGE-AIMoltbook Auto Post
Automate Moltbook posting with content generation and rate-limit compliance.
SKYLENAGE-AIClawdHub CLI
Search, install, update, and publish agent skills from clawhub.com.
SKYLENAGE-AIcurrency-converter
Convert currency amounts using live exchange rates from open APIs.
SKYLENAGE-AIstock-alerts
Monitor stock prices and notify when predefined thresholds are crossed.
SKYLENAGE-AItushare-finance
Fetch Chinese A-share market data from the Tushare Pro API.
SKYLENAGE-AISample API Integration Skill
Authenticate and call external REST APIs with retry and response parsing.
Frequently Asked Questions
FAQPage SchemaHow to install QwenClawBench?▼
Run `npx skills add SKYLENAGE-AI/QwenClawBench --all -g -y` in your terminal to install everything globally.
What does QwenClawBench measure?▼
It measures how well OpenClaw agents complete 100 realistic tasks across 8 domains, including workflow orchestration, system administration, finance, data analysis, and security.
How does QwenClawBench score agent performance?▼
It combines deterministic automated checks with an LLM judge in a hybrid mode, and zeroes out judge scores when basic deliverable checks fail to prevent inflated results.
Can I resume an interrupted benchmark run?▼
Yes. Re-run the same command with the same output directory to skip completed tasks, or add --rerun-anomalous to retry only failed tasks.
What do I need to run QwenClawBench?▼
You need Python 3.10 or later, Docker, the OpenClaw Docker image, and API credentials configured in the openclaw_config folder.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core