Module evaluator 

LLM-as-judge evaluator for benchmark datasets.

Evaluator runs each benchmark case against a subject model, then scores the responses in parallel using a separate judge model. Token budget enforcement and concurrency limits are applied per Evaluator::evaluate invocation.

Structs

CaseScore

Score for a single benchmark case.

EvalReport

Aggregate evaluation report returned by Evaluator::evaluate.

Evaluator

Evaluates a subject model against a benchmark dataset using an LLM judge.

JudgeOutput

Structured output returned by the judge LLM.