harveyai / harvey-labs

TL;DR

Harvey LAB is an open-source benchmark designed to evaluate the capabilities of large language model (LLM) agents in performing legal tasks. It provides a structured dataset and execution framework for assessing agent performance in realistic legal scenarios.

✦ Why It Matters

Explore Harvey LAB to benchmark your AI legal agents against real-world tasks today.

Key Takeaways

Explore the dataset to understand task requirements and scoring rubrics.
Utilize the execution harness to evaluate your LLM agents.
Contribute new tasks or improvements to enhance the benchmark.
Cite Harvey LAB in your research to support legal AI advancements.

How It Works

Harvey LAB operates by providing a structured framework that includes a task model, execution harness, and evaluation tools. Researchers can set up tasks, inspect them, run agents, and review scoring and reports through comparison dashboards.

harveyai / harvey-labs

BerriAI / litellm

tensorflow / tensorflow

open-webui / open-webui

Agentic data science with the Data Agent Kit

BerriAI / litellm

tensorflow / tensorflow

open-webui / open-webui

Agentic data science with the Data Agent Kit