#python

Harvey LAB is an open-source benchmark that tests how well AI agents can do real legal work, not just answer legal questions. It gives each agent instructions, case documents, and a required work product, then scores the result with expert rubrics. LAB includes more than 1,200 tasks across 24 legal practice areas. This helps you compare models, check agent quality, and build better legal AI tools with a realistic standard.

https://github.com/harveyai/harvey-labs