Find the mean, median, sum, min, max and count of your numbers.
Paste or type a list of numbers and this tool returns the three standard measures of centre, along with the count, sum, and the largest and smallest values. Each measure answers a slightly different question, and picking the wrong one is how statistics get used to mislead.
Take the set 4, 8, 15, 16, 23, 42.
With an even number of values the median is the average of the two central ones. With an odd count it is simply the middle value, so 4, 8, 15, 16, 23 has a median of 15.
| Measure | Best for | Weakness |
|---|---|---|
| Mean | Symmetric data with no extreme values; anything you later need to multiply back up | Dragged badly by outliers |
| Median | Skewed data — income, house prices, response times | Ignores the magnitude of everything except the middle |
| Mode | Categories and repeated discrete values — shoe sizes, ratings | May not exist, or there may be several |
The classic demonstration: nine people earn 30,000 and one earns 5,000,000. The mean income is 527,000, which describes nobody in the room. The median is 30,000, which describes nine of the ten. This is why income and house price statistics are almost always reported as medians, and why a mean is the right choice when a government wants a total to divide up but the wrong choice when a journalist wants to describe a typical person.
Two datasets can share a mean and be nothing alike. The sets {49, 50, 51} and {0, 50, 100} both average 50. Reporting only the centre hides that completely. The usual companion measures are the range, which is simply the largest value minus the smallest, and the standard deviation, which measures typical distance from the mean. This tool shows the minimum and maximum so you can see the range at a glance; if those two are far apart relative to the mean, treat the average with suspicion.
A plain mean assumes every value counts equally. Often they do not — a final exam worth 50% of a grade should not be averaged flat against a quiz worth 5%. For that you need a weighted mean:
Scores of 90 (weight 2), 75 (weight 3) and 60 (weight 5) give (180 + 225 + 300) / 10 = 70.5, whereas the unweighted mean is 75. Our GPA calculator does exactly this with credit hours as weights.
Some quantities give the wrong answer when you take a plain mean of them:
Numbers can be separated by commas, spaces or line breaks, so pasting a column straight out of a spreadsheet works. Decimals and negative numbers are handled. Non-numeric text is skipped rather than treated as zero — an important distinction, because counting a blank as zero would pull the mean down, whereas ignoring it means the count reflects only real observations. If your dataset genuinely contains zeros that matter, type them explicitly.
In everyday use they are the same thing — "average" almost always refers to the arithmetic mean. Strictly, average is a general term for any measure of centre, so the median and mode are also averages. When precision matters, say which one you mean.
Whenever the data is skewed or contains outliers. Income, property prices, waiting times and web page load times are all reported as medians because a small number of very large values would otherwise dominate the mean and describe nobody.
Yes. If two or more values tie for the highest frequency, the set is bimodal or multimodal and all of them are modes. If every value appears exactly once there is no mode at all.
Sort the values and take the mean of the two in the middle. For eight values that is the average of the fourth and fifth. The result may not be a value that appears in your data.
Yes, both. Values can be separated by commas, spaces or newlines, so a column copied from a spreadsheet can be pasted in directly.