Back to News
TencentJuly 23, 2026

WorkBuddy Bench

Open Source
code
agent
benchmark
swe
security

Explore WorkBuddy Bench

Visit the official website to learn more and get started

### TL;DR

WorkBuddy Bench is a multi-domain evaluation suite designed to test coding agents on realistic, complex tasks across software engineering, web development, office workflows, and security. It features 260 contamination-resistant tasks reverse-engineered from real-world commits and business scenarios to ensure agents are evaluated on genuine problem-solving capabilities rather than memorized data.

Key Insights & Metrics

Pricing
Free
Cost structure
Version
1.0
Current release version
Hardware
Requires local or cloud-based environment to run Docker containers (as defined in each task's environment/ directory)
Compute requirements
Category
Open Source
Licensing model
Region
China
Primary region

Key Features

  • 260 contamination-resistant tasks across Code, Web, Office, and Security domains
  • Tasks reverse-engineered from real-world commits, PRs, and business scenarios
  • Unified task-directory format with sandboxed Dockerized environments
  • Reproducible evaluation protocol compatible with CodeBuddy Code and Claude Code harnesses
  • Transparent and auditable open-source release including test cases and reference solutions

Discussion

0
Upvotes
0
Downvotes
0 reviews

Sign in to leave a review

Reviews

No reviews yet. Be the first to review!

🚀 Join the AI dev community — follow us everywhere

© 2026 MARKTECHPOST AI MEDIA INC. All rights reserved.Terms & ConditionsPrivacy Policy
Beta Mode