Confident AI / DeepEval icon

Confident AI / DeepEval

Open-source LLM evaluation framework (DeepEval) and managed platform from Confident AI for systematic testing. Confident AI offers DeepEval, an open-source LLM evaluation framework, and a managed platform for systematic LLM testing.

Visit Website Agent Runtimes & Platforms
runtime evaluation open-source testing

Overview

Open-source LLM evaluation framework (DeepEval) and managed platform from Confident AI for systematic testing.

Details

Confident AI offers DeepEval, an open-source LLM evaluation framework, and a managed platform for systematic LLM testing. DeepEval provides Python-based evaluation similar to pytest with metrics for hallucination, relevance, faithfulness, and many other dimensions.

Tags

runtime, evaluation, open-source, testing

Back to Agents