Python

llm-eval-harness

Deterministic evaluation of model answers: exact match, contains, token F1, ROUGE-L, and retrieval metrics, plus an optional LLM judge and a report renderer.

View on GitHub

CI passing · Python

llm-eval-harness

Highlights

Deterministic metrics: exact match, F1, ROUGE-L
Retrieval metrics
Optional LLM judge
Report renderer

Want the code?

View on GitHub