Z-Score Calculator

Use this Z-Score Calculator to enter values, adjust options, and review results in a compact responsive workspace.

Results are calculated automatically as you enter data.

What do you want to calculate?

Mean Standard deviation

Raw value x Standard deviation type

Formula and steps

Z-score -

The highlighted area updates with the selected z-score and region.

Disclaimer: All tools on this site are intended for educational and informational purposes only. Not professional advice or a decision tool. No guarantee of accuracy; verify data, assumptions, rules, model fit, and results before important use. See our Terms of Use.

Assumptions and limitations

Results are estimates for educational and exploratory use only and are not professional advice. No guarantee is made that outputs are accurate, complete, current, suitable, or error-free. Verify inputs, units, formulas, assumptions, rounding, data quality, model fit, and applicable rules independently. Do not rely on this calculator as the only basis for financial, legal, medical, safety, academic, business, official, eligibility, or regulated decisions; consult a qualified professional when stakes are material. Standard-normal probability results are numerical estimates computed with a stable normal-tail approximation and rounded for display. Verify model fit, data quality, and high-stakes decisions with validated statistical references or software. Use of this calculator is subject to our Terms of Use.

▼ See explanations and tips below ▼

Related Calculators

What Is a Z-Score?

A z-score, also called a standard score, tells you how far a raw value is from the mean in standard deviation units. Instead of saying only that a value is larger or smaller than average, a z-score tells you how large that difference is relative to the spread of the data.

For example, a value that is one standard deviation above the mean has a z-score of $1$. A value that is two standard deviations below the mean has a z-score of $-2$. A value exactly equal to the mean has a z-score of $0$.

Z-scores are useful because they put different measurements on a common scale. A score of 86 on one exam and a score of 185 centimeters in a height distribution are measured in very different units, but both can be described by how many standard deviations they are from their own means.

When the underlying distribution is normal, the z-score also connects directly to areas under the standard normal curve. Those areas can be interpreted as percentile ranks, left-tail probabilities, right-tail probabilities, two-tail probabilities, or probabilities between two z-scores.

Why Z-Scores Matter

Z-scores help answer questions that raw values alone cannot answer well:

Is this value above or below average?
How unusual is this value compared with the rest of the distribution?
How can two values from different scales be compared fairly?
What percent of a normal distribution is at or below this value?
What is the probability of being at least this far from the mean under a normal model?

This is why z-scores appear often in statistics courses, standardized testing, quality control, research analysis, education, psychology, business analytics, and any setting where values need to be interpreted relative to a distribution.

Key Terms to Know

Raw value $x$: The original value on the data scale, such as a test score, height, weight, time, or measurement.
Mean $\mu$ or $\bar{x}$: The center or average of the distribution. Population notation usually uses $\mu$; sample notation usually uses $\bar{x}$.
Standard deviation $\sigma$ or $s$: A measure of spread. Population notation usually uses $\sigma$; sample notation usually uses $s$.
Z-score $z$: A unitless value showing the number of standard deviations a raw value is above or below the mean.
Standard normal distribution: A normal distribution with mean $0$ and standard deviation $1$, often written as $Z \sim N(0,1)$.
Percentile rank: The percent of values in a distribution that are at or below a given value.
Left-tail probability: The probability that a standard normal value is less than or equal to a chosen z-score.
Right-tail probability: The probability that a standard normal value is greater than a chosen z-score.
Two-tail probability: The probability of being at least as far from $0$ as the chosen z-score, in either direction.
Between probability: The probability that a standard normal value falls between two z-scores.

How Z-Scores and Standard Normal Probabilities Work

The basic z-score formula subtracts the mean from the raw value, then divides by the standard deviation:

$$ z = \frac{x - \mu}{\sigma} $$

Where:

$x$ = raw value
$\mu$ = population mean
$\sigma$ = population standard deviation
$z$ = z-score

If you are using sample notation, the same idea is written as:

$$ z = \frac{x - \bar{x}}{s} $$

Where $\bar{x}$ is the sample mean and $s$ is the sample standard deviation.

The formula can also be reversed. If you know the mean, standard deviation, and z-score, you can convert the z-score back to a raw value:

$$ x = \mu + z\sigma $$

Or, using sample notation:

$$ x = \bar{x} + zs $$

Once a value has been standardized, normal probabilities are based on the standard normal distribution. If $Z \sim N(0,1)$, then the cumulative distribution function is written as $\Phi(z)$ and means:

$$ \Phi(z) = P(Z \le z) $$

That is the area to the left of the z-score on the standard normal curve.

Common probability regions are:

$$ P(Z \le z) = \Phi(z) $$

$$ P(Z \ge z) = 1 - \Phi(z) $$

$$ P(|Z| \ge |z|) = 2\left(1 - \Phi(|z|)\right) $$

$$ P(a \le Z \le b) = \Phi(\max(a,b)) - \Phi(\min(a,b)) $$

The standard normal curve itself is described by a density function:

$$ \phi(z) = \frac{1}{\sqrt{2\pi}}e^{-z^2/2} $$

The density is the height of the curve at a z-score. It is not the same thing as probability at a single exact point. For a continuous distribution, probabilities come from areas under the curve, not from the curve height alone.

Examples of Z-Scores in Practice

Example 1: Finding a Z-Score from a Raw Value

Suppose an exam has a mean of $72$ and a standard deviation of $8$. A student scores $86$.

Use the z-score formula:

$$ z = \frac{x - \mu}{\sigma} $$

Substitute the values:

$$ z = \frac{86 - 72}{8} $$

$$ z = \frac{14}{8} = 1.75 $$

The score is $1.75$ standard deviations above the mean. Under a normal model, a z-score of $1.75$ has a left-tail probability of about $95.99\%$, so about $4.01\%$ of values are above it.

Example 2: Converting a Z-Score Back to a Raw Value

Suppose a distribution has a mean of $100$ and a standard deviation of $15$. You want the raw value that corresponds to a z-score of $-1.2$.

Use the reverse formula:

$$ x = \mu + z\sigma $$

Substitute the values:

$$ x = 100 + (-1.2)(15) $$

$$ x = 100 - 18 = 82 $$

A z-score of $-1.2$ corresponds to a raw value of $82$. The negative z-score means the value is below the mean.

Example 3: Probability Between Two Z-Scores

A common normal-distribution question is the probability that a standard normal value falls between $-1$ and $1$.

Use the between-region formula:

$$ P(-1 \le Z \le 1) = \Phi(1) - \Phi(-1) $$

Using high-precision standard normal cumulative probabilities (retain the digits until the final subtraction):

$$ P(-1 \le Z \le 1) \approx 0.8413447460685429 - 0.1586552539314571 $$

$$ P(-1 \le Z \le 1) \approx 0.6826894921370858 $$

So about $68.26894921\%$ (usually reported as $68.27\%$) of a standard normal distribution falls between one standard deviation below the mean and one standard deviation above the mean. Rounding the two cumulative probabilities to four decimals first would give $0.6826$ and lose precision.

Example 4: Two-Tail Probability

A two-tail probability asks for the chance of being at least as far from the mean as a given z-score, in either direction. For $z = 2$:

$$ P(|Z| \ge 2) = 2\left(1 - \Phi(2)\right) $$

Since $\Phi(2) \approx 0.97725$:

$$ P(|Z| \ge 2) \approx 2(1 - 0.97725) $$

$$ P(|Z| \ge 2) \approx 0.0455 $$

That means about $4.55\%$ of a standard normal distribution is at least two standard deviations away from the mean, counting both tails.

How to Interpret the Result

A z-score has two important parts: its sign and its magnitude.

A positive z-score means the value is above the mean.
A negative z-score means the value is below the mean.
A z-score of zero means the value is exactly at the mean.
The absolute value of the z-score tells you the distance from the mean in standard deviation units.

For example, $z = 1.5$ is $1.5$ standard deviations above the mean, while $z = -1.5$ is $1.5$ standard deviations below the mean.

The percentile rank is the left-tail probability expressed as a percent. A percentile rank of $93.32\%$ means about $93.32\%$ of the standard normal distribution is at or below that z-score. It does not mean the value is $93.32\%$ of the maximum possible value.

Left-tail and right-tail probabilities are complements:

$$ P(Z \le z) + P(Z \ge z) = 1 $$

For continuous normal distributions, $P(Z < z)$ and $P(Z \le z)$ are the same for practical probability calculations because the probability at one exact point is zero.

A value around two standard deviations from the mean is noticeably far from the center under a normal model. A value around three standard deviations from the mean falls in a relatively far tail region under that model. These are descriptive interpretation guidelines, not universal rules or advice; the context and the shape of the real data still matter.

Common Mistakes and Misconceptions

Entering variance instead of standard deviation. Variance and standard deviation are related, but they are not the same input. If the variance is $64$, the standard deviation is $\sqrt{64} = 8$, not $64$.

Mixing units or scales. The raw value, mean, and standard deviation must all use the same scale. Do not enter a mean in centimeters, a raw value in inches, and a standard deviation in centimeters unless you convert them first.

Assuming the sample/population notation changes the arithmetic. Once you have already entered the mean and standard deviation, the z-score arithmetic is the same. The difference is the notation: population formulas use $\mu$ and $\sigma$, while sample formulas use $\bar{x}$ and $s$.

Confusing percentile rank with right-tail probability. A percentile rank is the area at or below the z-score. A right-tail probability is the area above the z-score. If the percentile rank is $95\%$, the right-tail probability is about $5\%$.

Misreading a two-tail result. The two-tail option means the two outside tails beyond $-|z|$ and $|z|$. It is not the area between $-|z|$ and $|z|$.

Using normal probabilities when the data are not normal enough. A z-score can describe distance from the mean for many kinds of data, but percentile and tail-probability interpretations depend on the normal-distribution model. Skewed, heavy-tailed, or multimodal data may not match normal probabilities well.

Rounding too early. Rounding the mean, standard deviation, or z-score too soon can change the final probability. Keep extra digits during intermediate steps when accuracy matters.

When to Use Z-Scores

Use z-scores when you need to:

Standardize a raw value relative to a mean and standard deviation.
Compare values measured on different scales.
Interpret how far a value is from the center of a distribution.
Convert between a raw value and a standard-deviation scale.
Estimate percentiles and tail probabilities under a normal model.
Understand normal-distribution examples in statistics, testing, quality control, or research.

Z-scores are especially helpful when a simple raw difference is not enough. A value that is $10$ units above the mean may be ordinary if the standard deviation is large, but unusual if the standard deviation is small.

Limitations and Things to Keep in Mind

A z-score depends on the mean and standard deviation you provide. If those inputs are estimated from a small, biased, outdated, or inappropriate dataset, the z-score may be misleading.

Normal-distribution probabilities are model-based. They assume the z-score is being interpreted using the standard normal distribution. If the real data are strongly skewed, have outliers, or follow a different distribution, the normal percentile and tail probabilities may not describe the real-world frequency accurately.

A standard deviation must be positive. A zero or negative standard deviation does not describe a valid spread for this calculation. Very tiny standard deviations can also produce unstable or unhelpful results because small differences from the mean create very large z-scores.

Probability results are numerical approximations. This calculator evaluates the standard normal CDF with the Abramowitz-Stegun 7.1.26 polynomial approximation; its displayed values are rounded. Standard normal cumulative probabilities generally do not have a simple closed-form expression, so tables and numerical methods can differ slightly in their last displayed digits.

The normal curve chart is a visual aid clipped to the displayed z-range; its visible ends are not probability boundaries. It helps show the selected area, but it should not replace the numerical probability. Very large positive or negative z-scores may be hard to judge from a chart because most of the visible curve is concentrated near the center.

This calculation does not prove that the data are normally distributed, compute the standard deviation from a dataset, convert measurement units, or solve inverse normal questions such as finding the z-score for a target percentile.

For decisions involving money, health, safety, engineering, legal obligations, official records, or high-stakes research, check the data source, confirm the model assumptions, and consult a qualified professional when needed.

How to Use This Calculator

Choose the calculation mode: find a z-score from a raw value, convert a z-score back to a raw value, or calculate a probability region.
For raw-value or z-score-to-value mode, enter the mean and standard deviation using the same scale or unit as the raw value. Probability mode works directly with standardized z-scores and does not use a mean, standard deviation, or raw value.
Choose population or sample notation for the raw-value and z-score-to-value workflows. This changes the displayed symbols, not the arithmetic after the standard deviation has already been entered.
For raw-value mode, enter the raw value.
For z-score-to-value mode, enter the z-score.
For probability mode, enter the z-score and choose left, right, two-tail, or between.
If you choose the between region, enter the second z-score.
Review the mode-appropriate result, probability estimates, interpretation, formula steps, and normal curve chart.

Frequently Asked Questions

What does a z-score of 0 mean?

A z-score of $0$ means the raw value is equal to the mean. It is neither above nor below average. Under the standard normal distribution, the left-tail probability at $z = 0$ is $50\%$.

Is a higher z-score always better?

Not always. A higher z-score means the value is farther above the mean, but whether that is good depends on the context. A high test score may be desirable, while a high defect rate, blood pressure reading, or processing time may not be.

What is the difference between a z-score and a percentile?

A z-score measures distance from the mean in standard deviation units. A percentile describes the percent of the distribution at or below a value. Under a normal model, the z-score can be converted to a percentile using the standard normal cumulative distribution.

What is the difference between left-tail and right-tail probability?

Left-tail probability is the area at or below the z-score. Right-tail probability is the area above the z-score. For a continuous normal distribution, the two add to $1$.

What does two-tail probability mean?

Two-tail probability is the probability of being at least as far from zero as the given z-score, in either direction. For example, a two-tail probability for $z = 2$ includes the area above $2$ and the area below $-2$.

Can I use z-scores for data that are not normally distributed?

You can use a z-score to describe how many standard deviations a value is from the mean, even when the data are not normal. However, percentile ranks and tail probabilities based on the standard normal curve should only be used when the normal model is appropriate enough for the question.

Does the population or sample standard deviation choice change the result?

The formula notation changes: population notation uses $\mu$ and $\sigma$, while sample notation uses $\bar{x}$ and $s$. If the same numeric mean and standard deviation are entered, the calculated z-score or raw value is the same.

Sources and References

Books

Barbara Illowsky and Susan Dean. Introductory Statistics 2e. OpenStax, Rice University, 2023. Chapter 6.1, “The Standard Normal Distribution,” and Chapter 6.2, “Using the Normal Distribution.” Chapter 6.1; Chapter 6.2.
Mine Çetinkaya-Rundel, David Diez, and Christopher Barr. OpenIntro Statistics. 4th ed., OpenIntro, Inc., 2019. Section 4.1, “Normal Distribution,” especially standardizing with Z-scores and finding tail areas. OpenIntro Statistics book page; Section 4.1 PDF excerpt.

Online and Official Sources

National Institute of Standards and Technology and SEMATECH. “Normal Distribution.” NIST/SEMATECH e-Handbook of Statistical Methods. Accessed July 4, 2026. NIST e-Handbook: Normal Distribution.
National Institute of Standards and Technology and SEMATECH. “Cumulative Distribution Function of the Standard Normal Distribution.” NIST/SEMATECH e-Handbook of Statistical Methods. Accessed July 4, 2026. NIST e-Handbook: Standard Normal CDF Table.