Home / Normal Distribution Calculator

Normal Distribution Calculator

Enter a value, a mean, and a standard deviation to get the exact area under the bell curve on either side.

Numbers in

Numbers out

Z-score--
P(X < x)--
P(X > x)--

The panel recalculates the moment you change a field; no data leaves your browser.

How to read it

The normal distribution is the familiar bell curve, symmetric around the mean. This calculator converts your value to a z-score, then finds the area under the curve to its left using the error function, which is mathematically equivalent to the cumulative probability.

Formulas: z = (x − mean) / standard deviation. P(X < x) = 0.5 × (1 + erf(z / √2)). P(X > x) = 1 − P(X < x).

For the defaults (x = 1.5, mean = 0, SD = 1): z = 1.5000; P(X < 1.5) = 93.32%; P(X > 1.5) = 6.68%. A z-score of 1.5 lands close to the 93rd percentile of the distribution.

The empirical rule, computed exactly

The familiar "68-95-99.7" shorthand rounds off; here is what this calculator's own erf-based method returns at exactly 1, 2, and 3 standard deviations from the mean:

WithinShare of the distribution
1 standard deviation68.27%
2 standard deviations95.45%
3 standard deviations99.73%

Notice these are slightly different from the rounded "68-95-99.7" most textbooks quote; the difference shows up past the second decimal. See the z-score calculator for the percentile framing of the same math, or the probability calculator for binomial and Poisson alternatives when your data isn't continuous.

Related calculators

Good to know

FAQs

What is the 68-95-99.7 rule, and does this calculator use it?

It's a rounded shorthand for how much of a normal distribution sits within 1, 2, and 3 standard deviations of the mean. This calculator doesn't rely on the rounded version; it computes the exact cumulative probability with the error function for whatever x, mean, and SD you enter, so results for values in between the whole-SD marks are just as precise.

Why do P(X < x) and P(X > x) always add up to 100%?

Because every outcome falls on one side of x or the other; together they cover the entire distribution. The calculator computes P(X < x) directly and simply subtracts it from 1 to get P(X > x), so the two will always sum to exactly 100% by construction.

Can I use this for data that isn't actually bell-shaped?

No, not reliably. Every formula here assumes a symmetric, bell-shaped distribution. Skewed data, like income or wait times, will give you a technically computed but practically misleading answer if you force it through a normal-distribution calculator instead of checking the shape first.

What happens if I set the standard deviation to zero?

The calculator stops and shows placeholder dashes instead of a number. A standard deviation of zero means every value in the distribution is identical, which breaks the z-score formula's division step, so the tool declines to guess rather than return a meaningless result.