FICHA · AUR

python-pydantic-evals

Framework for evaluating stochastic code execution, especially code making use of LLMs.

  • LLM evaluation framework
  • LIBRARY
  • AI
  • TESTING
  • Dependency only
official+codex · reviewed · Jun 3, 2026 description in en

Description

Stochastic code and LLM-backed behavior can be evaluated with repeatable test workflows. AI developers use pydantic-evals for model regression checks, agent scoring, datasets, and quality experiments. Evaluation inputs and outputs may include sensitive prompts or generated content.

Permissions

Permissions not analysed for this source yet.