BLEU Score Calculator
Calculate the BLEU score to evaluate machine translation or text generation quality.
About BLEU Score Calculator
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))
Worked example
With the default values below, BLEU Score Calculator returns BLEU Score of 0.4635. Change any input above and every figure here is recalculated in your browser.
Inputs used
- Unigram Precisionaccepts 0–1
- 0.85
- Bigram Precisionaccepts 0–1
- 0.65
- Trigram Precisionaccepts 0–1
- 0.45
- 4-gram Precisionaccepts 0–1
- 0.3
- Candidate Lengthminimum 1
- 25
- Reference Lengthminimum 1
- 28
Results
- BLEU Score
- 0.4635
- Brevity Penalty
- 0.8869
- Geometric Mean Precision
- 0.5226
Step by step
- 1Brevity Penalty= 0.886920
- 2Geometric mean of precisions= 0.522597
- 3BLEU = BP × geometric mean= 0.463502
Assumptions and limits
- The result is derived only from the 6 inputs listed above. Anything not among them is not part of the calculation.
- In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
- Figures are rounded for display to 4 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.
How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.
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.