Skip to content
Calcrivo

BLEU Score Calculator

Calculate the BLEU score to evaluate machine translation or text generation quality.

Inputs

BLEU Score

0.4635

Brevity Penalty

0.8869

Geometric Mean Precision

0.5226

Step by step

  1. Brevity Penalty

    exp(1 − 28/25)

    = 0.886920

  2. Geometric mean of precisions

    exp((ln0.85 + ln0.65 + ln0.45 + ln0.30)/4)

    = 0.522597

  3. BLEU = BP × geometric mean

    0.8869 × 0.5226

    = 0.463502

How it works

BLEU (Bilingual Evaluation Understudy) measures machine translation quality by computing the geometric mean of n-gram precisions (1 through 4), multiplied by a brevity penalty to prevent artificially short translations from scoring high. Scores range from 0 to 1, with higher being better.

Formula

BLEU-4

BLEU = BP * exp((1/4) * sum(ln(p_n)))

p_n
Modified n-gram precision for n=1..4
BP
Brevity penalty: min(1, exp(1 - ref_len/cand_len))

Frequently Asked Questions

What is a good BLEU score?

BLEU scores above 0.3 are generally considered decent for machine translation, above 0.5 is very good, and scores above 0.6 are near human-level for many language pairs. The absolute number depends heavily on language pair and domain.

Why use geometric mean instead of arithmetic mean?

Geometric mean is more sensitive to low individual precisions — if any n-gram precision is zero, the entire BLEU score drops to zero, enforcing that good translations must match at all n-gram levels.

You might also need