Glossary
LLM evaluation
Structured scoring of how your product uses a language model: answers, tools, retrieval, and safety — on a named build.
LLM evaluation is not a foundation-model bake-off. If you cannot pin prompt, model, and index versions, you are scoring a vibe.
Related
Talk to our QA team
Ready to discuss your testing needs?
Tell us about your product and where quality matters most. We will help you decide the right testing approach.