Percentile Calculator
Paste a list of numbers and pick a percentile — get the kth percentile by linear interpolation, with the sorted data, the rank and every step shown.
Reviewed by the OmniCalc teamMethod verified 2026-07-01
8 values
7.6
90th percentile 7.6- Percentile (k)
- 90%
- Count (n)
- 8
- Percentile value
- 7.6
Show steps
- Sort the 8 values in ascending order: 2, 4, 4, 4, 5, 5, 7, 9.
- Find the rank: r = (k ÷ 100) × (n − 1) = (90 ÷ 100) × (8 − 1) = 6.3.
- Interpolate between the neighbours: 7 + 0.3 × (9 − 7) = 7.6.
How to use the percentile calculator
- 1Type or paste your data set — separate values with spaces, commas or new lines.
- 2Enter the percentile (k) you want, from 0 to 100 — for example, 90 for the 90th percentile.
- 3Read the percentile value, and open Show steps to see the sort, the rank and the interpolation.
Percentiles in one line
The kth percentile splits the sorted data so that about k% of it falls below. The 25th and 75th percentiles are the quartiles, and the 50th is the median. When the rank lands between two values, the calculator interpolates linearly between them.
Frequently asked questions
What does the kth percentile mean?
The kth percentile is the value below which roughly k% of the data falls. The 90th percentile, for example, is the point that about 90% of your numbers sit at or below — a common way to describe a high-but-not-extreme value.
Which method does this calculator use?
Linear interpolation between closest ranks, known as the R-7 method. It is the same definition Excel's PERCENTILE.INC and NumPy's default percentile use, so results match those tools. Some textbooks use a nearest-rank rule instead, which can give a slightly different value.
How is the percentile actually computed?
The data is sorted ascending and a rank r = (k ÷ 100) × (n − 1) is found, where n is the count. If r is a whole number the percentile is the value at that position; otherwise it is interpolated between the two neighbouring values in proportion to the fractional part of r.
Is the 50th percentile the same as the median?
Yes. The 50th percentile equals the median — the middle value once the data is sorted. Entering 50 for k reproduces the median exactly.