DeepEval
LLM evaluation framework — 14+ metrics
About
Open-source evaluation framework with 14+ metrics including faithfulness, relevancy, and hallucination detection. Integrates with CI/CD.
Choose DeepEval when…
- •You want a pytest-style framework for LLM testing
- •Unit-test-like evals for LLM outputs fit your workflow
- •You need RAG-specific metrics like faithfulness and relevancy
Builder Slot
Tests, evals, and experiment tracking to measure and improve your AI output quality
Stack Genome Detection
AIchitect's Genome scanner detects DeepEval in your project via these signals:
deepevalCONFIDENT_API_KEYIntegrates with (2)
DeepEval sends evaluation results to Langfuse as trace scores via its Langfuse integration.
→ Quality metrics — faithfulness, hallucination rate, G-Eval scores — visible alongside the raw traces that produced them.
DeepEval uses OpenAI's API as the judge model to score generated outputs on metrics like faithfulness, relevance, and hallucination rate.
→ LLM-as-judge quality metrics powered by GPT-4o — structured, reproducible evaluation scores for any AI output.
Often paired with (1)
Alternatives to consider (4)
Pricing
In 2 stacks
Ruled out by 1 stack
Badge
Add to your GitHub README
[](https://aichitect.dev/tool/deepeval)Explore the full AI landscape
See how DeepEval fits into the bigger picture — browse all 207 tools and their relationships.