1. Home
  2. Calculate
  3. Z-Score Calculator

Z-Score Calculator

z-score, normal percentile and T-score in one place, and back again.

Runs in your browser · No upload
z-score
1
z = (115 − 100) ÷ 15
Percentile P(Z ≤ z)
84.1345%
Upper tail P(Z ≥ z)
15.8655%
Two-tailed probability (p-value)
0.317311
Probability within mean ± |z|σ
68.2689%
T-score (mean 50, SD 10)
60
Mean 100, SD 15 score (IQ scale)
115
Mean 100, SD 20 score
120
Probabilities assume a normal distribution. If your data is far from normal, the percentile can differ from reality.

How to use

  1. Value to z-score: enter your value, the mean and the standard deviation. On a test with mean 70 and standard deviation 10, a score of 85 gives z = 1.5.
  2. From a data set: paste a list of numbers and the tool computes the mean and standard deviation itself, then shows the z-score of your value and a table with every data point. Use the population SD if the list is the whole group, or the sample SD if it is a sample drawn from a larger group.
  3. Percentile to value: enter the percentile you want (for the top 10%, enter 90) and the tool works backwards to the value at that spot for your mean and standard deviation.
  4. Below the result you also see the percentile under a normal distribution, the upper-tail share, the two-tailed probability and the T-score.

What a z-score is

A z-score tells you how many standard deviations a value sits from the mean.

z = (x − μ) ÷ σ

Here x is your value, μ the mean and σ the standard deviation. A z of 0 is exactly average, +1 is one standard deviation above, and −2 is two below. Because z-scores have no units, they let you compare things measured on different scales, like a test score and a height.

Normal distribution and percentiles

If the data follows a normal (bell-shaped) distribution, each z-score maps to a cumulative probability.

z Percentile Upper tail
−1 about 15.87% about 84.13%
0 50% 50%
1 about 84.13% about 15.87%
1.5 about 93.32% about 6.68%
1.96 about 97.50% about 2.50%
2 about 97.72% about 2.28%
3 about 99.87% about 0.13%

About 68.27% of values fall within ± 1σ of the mean, 95.45% within ± 2σ and 99.73% within ± 3σ. The familiar critical value 1.96 is where the two tails together hold 5%.

T-scores and other standard scores

These move the z-score onto a scale with a fixed mean and standard deviation.

Name Formula Mean, SD
T-score 50 + 10z 50, 10
IQ-style score 100 + 15z 100, 15
Mean 100, SD 20 score 100 + 20z 100, 20

For example, z = 1.5 is a T-score of 65, or 130 on the mean 100, SD 20 scale. Real exam scores follow the rules of the testing body, so treat these values as conversions and not as official scores.

Things to keep in mind

  • Percentiles and upper-tail shares assume a normal distribution. If the data is heavily skewed, the real rank can differ.
  • If the standard deviation is 0 (all values equal), z-scores are undefined.
  • In the data box, a comma inside a number such as 1,234 is read as a thousands separator and other commas separate values. When in doubt, put one number per line.
  • For the mean, median and variance see the average calculator, and for interval estimates the confidence interval calculator.

FAQ

Is a higher z-score always better?

A z-score only shows distance from the mean. For test scores higher is better, but for something like a race time, lower is better, so the meaning flips.

Population or sample standard deviation?

Use the population SD (divide by n) when your data is the entire group, and the sample SD (divide by n−1) when it is a sample from a bigger group. The smaller the sample, the bigger the gap between them.

What percentile is a z-score of 2?

About the 97.72nd percentile under a normal distribution, which leaves roughly 2.28% above.

Is my input stored anywhere?

No. Your numbers are processed in your browser only and never sent to a server.

Can't find the tool you need?

Tell us what you want to do. We build the most requested tools first.