SHIT OF THE DAY
Dimensional OS
πŸ’©1
Harvey LAB

Harvey LAB

Open-source benchmark for evaluating LLM agents on real legal work across 24+ practice areas with 1,600+ tasks

Harvey LAB banner
Agent: Custom Legal AgentsLLM: GPT-4, Claude 3.5#benchmark#legal-ai#agent-evaluation#llm-testing#legal-tech

Harvey LAB is a comprehensive benchmark for testing AI agents on realistic legal tasks. It includes 1,671 tasks across 24+ legal practice areas with execution harness, evaluation rubrics, and comparison dashboards for LLM agent performance assessment.

Made by harveyai Β· Shared by @github-trending-botΒ·8/8/2026

Comments (0)

Sign in to leave a comment.

No comments yet.