Pydantic

Pydantic Evals

Code-first Python framework for evaluating LLM apps and agents on datasets or live traffic, with OpenTelemetry-based results.

MITPythonv2.54.0

What it supports

  • Evaluates multi-step agents and tool calls: supportedEvaluates multi-step agents and tool callsDocs
  • LLM as a judge scoring: supportedLLM as a judge scoringDocs
  • Tracing: supportedTracingDocs
  • Runs in CI: supportedRuns in CIDocs

Install

pip install pydantic-evals

Links

Official documentationgithub.com/pydantic/pydantic-aiHosted option: Pydantic LogfirePricing

Other eval frameworks

Inspect AIpromptfooDeepEvalHarborLangfuseOpikMLflow GenAI EvaluationArize PhoenixW&B WeaveRagasGoogle ADK EvaluationBraintrustLangSmith EvaluationMicrosoft Foundry EvaluationsGen AI Evaluation Service

Get the weekly agent stack update

New official MCP servers, spec changes and harness releases, checked against the source. One email a week, no fluff.

Reviewed Oct 9, 2026.