Hallucination rate
How often a system makes things up, measured on a set of test tasks.
The fuller definition
A hallucination rate is a measurement of unsupported or false outputs under a specified definition, task set, and counting method.
Multiple-choice questions, general knowledge, clean text, scored automatically.
Scanned letters, conditional dates, two conflicting sources, scored by a lawyer.
The first number is real for the test it describes. It is not a prediction of the second. Run a small test on your own material before treating a headline score as evidence.
A concrete example
An evaluator counts unsupported factual statements in a defined set of generated summaries.
The distinction that matters
Different definitions and denominators produce different rates; a single vendor percentage is not universal reliability.
Related terms
Hallucination
When the model states something that sounds right but is made up, including cases, quotes, and facts that do not exist.
Reliability & securityEvaluation (eval)
Testing an AI tool on a set of tasks to see how well it actually does.
Reliability & securityBenchmark
A standard test used to compare models. A high score on it does not mean the model is good at your task.
Where it is taught
Test an AI workflow on work you can assessSource and further reading
Anthropic · Evaluating AI agentsThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.