Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Judges is a library for using and creating LLM-as-a-Judge evaluators, providing curated classifiers and graders backed by research. It offers a low-friction interface for evaluating LLM outputs through boolean classifiers, numerical or Likert scale graders, and a Jury object for combining multiple judges.
Parse Score