Skip to content
Eval Suites50

DeepEval

Pytest-style LLM testing with 50+ metrics for RAG, agents, and custom G-Eval rubrics.

DeepEval at a glance

Maintainer
Confident AI
Size
Tool (50+ metrics)[1]
Category
Harnesses & Runners
Runs with
DeepEval / Pytest
License
Apache-2.0
Tier
starter

Failure modes DeepEval catches

Unfaithful RAG
Task failure
Rubric misses

Starter command

A starting point, not a guarantee. Commands change between releases, so confirm against the official README.

DeepEval starter
pip install deepeval
deepeval test run test_app.py

Sources

  1. 1. DeepEval official page or repository · Confident AI · Repository · Sources checked