Free to use No registration 100% private Instant results Metric & Imperial

Z-Score Calculator

A z-score answers the question "how unusual is this, really?" by expressing any raw number as how many standard deviations it sits from the average. An 85 on a test means nothing until you know the class averaged 75 with a standard deviation of 10 — then 85 is exactly one standard deviation above, putting it in the top ~16%. Enter your value, the mean, and the standard deviation to get the z-score and its true percentile, or flip it: enter a target percentile to find the cutoff score.

Score to Z-Score

must be > 0

Reverse: Target Percentile → Score

e.g. 90 for "top 10%" cutoff

The Z-Score Formula

Standardizing a value strips away its original units and expresses position relative to the spread of the data:

z = (x − μ) ÷ σ

Reverse it to recover a raw score from a target percentile: x = μ + z × σ, where z is the standard normal cutoff for that percentile (about +1.28 for the 90th, +1.645 for the 95th, +1.96 for the 97.5th). Because the standard normal is symmetric, the 5th percentile is just the negative of the 95th.

Worked Example: An 85 on a Tough Exam

The class averaged 75 with a standard deviation of 10. Your 85 gives z = (85 − 75) ÷ 10 = +1.00, which lands at the 84.1th percentile — you beat about 84% of the class. Now suppose the department awards the top 10% a prize. The 90th percentile needs z ≈ 1.282, so the cutoff score is 75 + 1.282 × 10 = 87.82. Your 85 falls just short; you'd need roughly an 88 to make the cut. Same distribution, two completely different stories depending on which direction you read it.

When Z-Scores Are (and Aren't) the Right Tool

Z-scores assume the data are at least roughly symmetric and bell-shaped. For genuinely skewed distributions (income, house prices), the mean and standard deviation are themselves misleading, and a percentile rank from the raw data (or a log transform) is more honest. For test scores, heights, measurement errors, and most naturally-occurring biological and industrial metrics, the normal assumption behind this calculator is a very good approximation.

Frequently Asked Questions

What is a z-score?

It's how many standard deviations a value is from the mean: z = (x − μ) ÷ σ. It puts values from different scales on a common footing.

How do you interpret a z-score?

Sign = direction from mean; magnitude = distance in SDs. ~68% of values sit within ±1, 95% within ±2, 99.7% within ±3.

What percentile does a z-score correspond to?

The area under the normal curve to the left of z. z = 1.00 → 84.1th percentile; z = −1.00 → 15.9th. We compute it via the normal CDF.

Can a z-score be negative?

Yes — any value below the mean is negative. A 60 with mean 75, SD 10 gives z = −1.5 (about the 6.7th percentile).

How do you find the value at a given percentile?

Use x = μ + z × σ with the inverse-normal z for that percentile. Enter a target % and the tool returns the cutoff score.

B
BuildFormulas Math & Statistics Team
Statistics & Data Analytics

The BuildFormulas Math & Statistics Team builds practical statistical tools for students, researchers, and analysts, with exact normal-distribution computations.

Reviewed by BuildFormulas Editorial Review Board, Editorial Review
Last updated: August 2026