Skip to content
Owais Khan Software Reviews

NPS Calculator

Net Promoter Score, margin of error and whether a change is real.

Calculate your NPS

This survey
Previous survey (optional)

NPS

+35

100 responses

95% margin of error

±14.8

20.2 to 49.8

Change vs previous

+20

not statistically significant (p = 0.07)

Responses for ±5

873

at this promoter/detractor split

Everything stays on this device — your survey data never leaves your browser.

Net Promoter Score calculator

Net Promoter Score is the share of customers who would recommend you minus the share who would not. Enter your promoter, passive and detractor counts, or paste the raw 0–10 answers and let the calculator bucket them. The example survey of 100 responses scores +35.

NPS margin of error

A survey is a sample, so every NPS score has a margin of error that shrinks as responses grow. With 100 responses the example is +35 ± 14.8: the true score plausibly lies anywhere from 20.2 to 49.8. Most NPS tools show a single number; the range is what tells you how much to trust it.

Did your NPS really change?

Add last quarter’s counts to test the change. The example rose 20.0 points, which sounds like a win, but with 100 responses in each survey it is not statistically significant (p = 0.07). You would need many more responses, or a larger shift, before calling it real.

Collecting NPS responses

NPS surveys usually live in your CRM or help desk. Our comparisons cover CRM for call centers and CRM for ecommerce, and the CRM section lists the rest.

Frequently asked questions

How do I calculate NPS?
Survey customers with “How likely are you to recommend us to a friend or colleague?” on a 0–10 scale. Take the percentage who answered 9–10 (promoters) and subtract the percentage who answered 0–6 (detractors); passives (7–8) are ignored. In the example, 52% promoters minus 17% detractors gives an NPS of +35. The result runs from −100 to +100 and is written as a whole number, not a percentage.
What counts as a promoter, passive and detractor?
Promoters scored 9 or 10, passives 7 or 8, and detractors 0 to 6. The cut-offs are part of the standard Net Promoter System, so changing them gives a number that is not comparable with other companies’ NPS. Passives are satisfied but unenthusiastic: they do not count toward either side, but they do raise the number of responses, which shrinks both percentages.
What is a good NPS score?
There is no universal threshold. Above 0 means you have more promoters than detractors, but typical scores differ widely between industries, company sizes and survey methods, so published “good NPS” benchmarks are only loose guides. The comparison that matters most is your own score over time, measured the same way, and against direct competitors if you can find figures collected with the same question.
How many responses do I need for a reliable NPS?
It depends on how precise you need to be. The margin of error shrinks with the square root of the number of responses: for the example split (52.0% promoters, 17.0% detractors) you would need 873 responses to be within ±5 points at 95% confidence, while 100 responses give ±14.8. Enter your target margin in the calculator to see the number for your own split.
Is a change in NPS statistically significant?
Not automatically. Each survey has a margin of error, and two scores can differ by chance. The calculator compares two independent surveys with a two-sided z-test on the difference. In the example NPS rose 20.0 points (from +15 to +35), but with 100 responses each that is not statistically significant (p = 0.07). Leave the previous-period fields empty to skip the test.
Can NPS be negative?
Yes. NPS ranges from −100 (every respondent is a detractor) to +100 (every respondent is a promoter). A negative score means detractors outnumber promoters. Because passives count in neither group, a score of 0 does not mean “neutral” customers: it means promoters and detractors are equally common.
Is my survey data uploaded or processed on a server?
No. The score is calculated inside this page, everything you enter never leaves your browser, and there is no sign-up. Your numbers are saved only in this browser so they are still here when you return; Clear removes them. That is enforced rather than promised: this site’s test suite scans the shipped HTML for every browser API capable of sending data off the page and fails the build if it finds one.