One Number That Compares Anything to Anything
You scored 85 on a test where the class averaged 70. Good? Now compare: your friend scored 120 where her class averaged 100. Who did better relative to their class? Raw scores cannot answer that — z-scores can.
A z-score counts how many standard deviations a value sits from the mean: z = (x − μ) / σ. This calculator returns the z-score, the percentile, and a plain-English read of how unusual your value is — the 68-95-99.7 rule, applied to your numbers.
z = (x − μ) / σ · percentile · interpretation
? What does a z-score actually tell me?
A z-score counts how many standard deviations a value sits from the mean. z = +1.5 means 1.5 standard deviations above average; z = −0.8 means 0.8 below.
The percentile translates that into plain language: a z of +1.0 is roughly the 84th percentile — the value beats about 84% of the population (assuming a normal distribution).
About 68% of values fall within z = ±1, about 95% within ±2, and 99.7% within ±3 (the empirical rule).
Please enter valid numbers, with a standard deviation greater than zero.
Percentiles assume a roughly normal distribution. For skewed data, the z-score still standardizes the value but the percentile reading becomes approximate.
How to Use the Z-Score Calculator
- Enter the raw score (x) — the value you want to standardize.
- Enter the population mean (μ) and standard deviation (σ).
- Click Calculate Z-Score.
- Read the result: the z-score, percentile rank, and how far from typical your value sits.
The Z-Score Formula
x = raw score, μ = population mean, σ = standard deviation
Percentile ≈ Φ(z) × 100, where Φ is the standard normal CDF
Worked example: x = 85, μ = 70, σ = 10. z = (85 − 70)/10 = +1.5 — 1.5 standard deviations above the mean, roughly the 93rd percentile: better than about 93% of the population.
Z-Score Quick Reference
| z | Percentile (≈) | Meaning |
|---|---|---|
| −2.0 | 2nd | Well below average |
| −1.0 | 16th | Below average |
| 0 | 50th | Exactly average |
| +1.0 | 84th | Above average |
| +1.5 | 93rd | Well above average |
| +2.0 | 98th | Unusually high |
| +3.0 | 99.9th | Extremely unusual |
Where Z-Scores Are Used
Education: comparing test scores across different exams or classes. Medicine: growth charts and lab results are reported as z-scores. Finance: the Sharpe ratio is essentially a z-score of returns. Quality control: flagging measurements beyond ±3σ as defects. Sports analytics: comparing athletes across eras.
The percentile reading assumes a roughly normal distribution. For skewed data the z-score still standardizes, but treat the percentile as approximate.
Comparing Two Scores on Different Scales
Raw scores from different tests cannot be compared directly — but their z-scores can. Say you scored 85 on a test with mean 70 and standard deviation 10: z = (85 − 70) ÷ 10 = +1.50, about the 93rd percentile. Your friend scored 120 on a different test with mean 100 and standard deviation 15: z = (120 − 100) ÷ 15 = +1.33, about the 91st percentile. Despite scoring 35 points less on paper, you rank higher relative to your class.
Two reading rules make z-scores intuitive. The sign tells you which side of the mean you are on: positive is above, negative is below. The size tells you how unusual the value is: about 68% of values fall within ±1 of the mean, values beyond ±2 sit in roughly the outer 5%, and values beyond ±3 in the outer 0.3% — rare enough to double-check.
From a Z-Score Back to a Raw Score
Raw score = mean + (z-score × standard deviation)
Worked example: in that same class (μ = 70, σ = 10), a z-score of +2 converts back to 70 + 2 × 10 = 90. Working from a target percentile runs the same way: the 95th percentile needs z ≈ 1.645, so the score to beat is 70 + 1.645 × 10 = 86.45 — call it 87. Landmarks worth memorizing: 90th percentile z ≈ 1.28, 95th z ≈ 1.645, 99th z ≈ 2.33. One caution while you work with them: a percentile is not a percentage score. Sitting at the 95th percentile does not mean 95% correct — it means you stand ahead of 95% of the group you are compared with.
Area Above, Below and Between Two Scores
A percentile is just the area below a z-score, so areas combine by subtraction. The share of values above z = +1.5 is 100 − 93.32 = 6.68%. The share between z = −1 and z = +1 is 84.13 − 15.87 ≈ 68.3% — which is where the empirical rule’s famous 68% comes from. Any “between two scores” question is two percentile lookups and one subtraction. The same subtraction answers everyday scale questions too: on an IQ-style scale (μ = 100, σ = 15), the middle 68% runs from z = −1 to z = +1 — scores of 85 to 115 — which is exactly why results in that band are described as average, and why a score of 130 (z = +2) lands in roughly the top 2%.
Frequently Asked Questions
How do you calculate a z-score?
Subtract the mean from the value and divide by the standard deviation: z = (x − μ) / σ. Example: (85 − 70) / 10 = +1.5.
What does a z-score of 1.5 mean?
The value is 1.5 standard deviations above the mean — roughly the 93rd percentile, meaning it beats about 93% of a normal population.
What is a good z-score?
It depends on context: near 0 is average, beyond ±2 is unusual (top/bottom ~2.5%), beyond ±3 is extremely unusual. In quality control, | z | > 3 often flags a defect.
Can z-scores be negative?
Yes — negative means below the mean. z = −1.0 is one standard deviation below average (about the 16th percentile).
What is the difference between z-score and percentile?
The z-score counts standard deviations from the mean; the percentile translates that into the percentage of the population below the value. They describe the same position in different units.
Do z-scores require a normal distribution?
Strictly, the percentile interpretation does — it uses the normal CDF. The z-score itself is just standardization and works on any data, but percentiles become approximate when data are skewed.
How do I convert a z-score back to a raw score?
Use the reverse formula x = μ + z × σ: multiply the z-score by the standard deviation, then add the mean. A z-score of +2 in a class with mean 70 and standard deviation 10 converts back to 70 + 2 × 10 = 90.
What z-score corresponds to the 95th percentile?
About 1.645. Roughly 95% of values in a normal distribution fall below z = 1.645, which is why that figure turns up in so many confidence-interval and grading calculations. Nearby landmarks: 1.28 for the 90th percentile and 2.33 for the 99th.
Should I use the population or sample standard deviation?
Use the population standard deviation (dividing by n) when your data cover the whole group you care about — say, every student in one class. Use the sample standard deviation (dividing by n − 1) when your numbers are a sample standing in for a larger population; it widens the spread slightly and shrinks the z-scores a little.
Final Thoughts
Z-scores are the universal translator of statistics: test scores, lab results, returns, defects — all comparable once standardized. Compute yours, check the percentile, and you will know exactly where you stand.
Standardized? Keep Exploring Stats
Try our standard deviation calculator and average calculator.