Live Comparison

The same candidate and reference, judged by BLEU and ROUGE.

Candidate
Reference

All seven metrics

What each metric scores, what it needs, and where it differs.

Metric Family Measures Needs human reference/labels? Range Best for
PrecisionClassificationCorrectness of positive predictions Yes0 → 1Low-false-alarm tasks
RecallClassificationCoverage of real positives Yes0 → 1Low-miss tasks
F1ClassificationBalance of precision & recall Yes0 → 1Imbalanced classes
PerplexityProbabilisticModel surprise on held-out text No1 → ∞ (lower better)Comparing LMs
BLEUReference overlapN-gram precision + brevity Yes0 → 1Machine translation
ROUGEReference overlapN-gram / LCS recall Yes0 → 1Summarisation
LLM-as-judgeModel-gradedRubric quality via an LLM Optionalrubric-definedOpen-ended quality