Developer Tools
LLM Eval Scorecard
Score LLM outputs manually across accuracy, completeness, instruction following, safety, and clarity.
Overall score
89.1% (B)
4/5 · w3
4/5 · w2
5/5 · w3
5/5 · w2
4/5 · w1
Manual scorecard only. Brevio does not send outputs to an evaluator model or store your notes.
How to Score LLM Outputs with a Manual Eval Scorecard
Build a practical rubric for LLM output evaluation across accuracy, completeness, instruction following, safety, and clarity.