Apps & Tools
SWE-COWORK
A multi-agent software engineering benchmark simulating an IT company environment.
Is this your creation?
Description
A complex evaluation environment that drops AI agents into a simulated company with 26 colleagues, 101 repositories, and a shared task board. It tests models like Claude Opus 5.5 and GPT-6 Astra on their ability to coordinate, ask the right owners for information, and take accountability for broken code across a large-scale project.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.