Reverzereverze

A/B Test Sample Size Calculator

Free Calculator

Find how many visitors each variant needs to detect your target uplift β€” at 95% significance and 80% power. Instant and private.

100% private

Runs in your browser β€” no numbers leave your device.

Your test parameters

%

Your current conversion rate (control).

%

The smallest RELATIVE uplift you want to detect (e.g. 20% = 5% β†’ 6%).

Sample size per variant

8,146

Visitors each variant (A and B) needs before you can trust the result at 95% significance / 80% power.

Total sample size

16,292

Both variants combined (A + B).

Target conversion rate (B)

6.00%

The rate variant B must reach to hit your uplift.

How it works

1

Enter your baseline

Add your current (control) conversion rate.

2

Set the uplift

Enter the minimum relative improvement you want to detect.

3

Read the sample size

See the visitors needed per variant, updated live.

4

Plan the test

Divide by your daily traffic to estimate how long to run it.

Give every test a stronger variant

Reverze generates A/B screenshot variants so your tests compare real, distinct creative.

How does an A/B test sample size calculator work?

An A/B test sample size calculator tells you how many visitors each variant needs before a result is trustworthy. It works backward from three things: your baseline conversion rate, the minimum uplift you want to be able to detect, and your confidence and power targets. This tool fixes the two conventional targets β€” 95% statistical significance (a 5% false-positive rate) and 80% power (a 20% chance of missing a real effect) β€” and solves the two-proportion formula for the sample size per variant.

The smaller the effect you want to detect and the lower your baseline rate, the more traffic you need β€” often dramatically more. That is why bold creative changes are easier to prove than tiny tweaks: a bigger expected uplift needs a smaller sample. Enter realistic numbers, then divide the per-variant sample by your daily traffic to see how many days the test must run before you stop peeking and call it.

Frequently asked questions

How does an A/B test sample size calculator work?
It solves the two-proportion sample-size formula. Given your baseline conversion rate and the minimum relative uplift you want to detect, it computes the visitors needed per variant to reach 95% significance and 80% power β€” the industry-standard defaults this tool uses.
What is the minimum detectable effect?
The minimum detectable effect (MDE) is the smallest relative improvement you want the test to be able to catch β€” for example, 20% means going from a 5% to a 6% conversion rate. A smaller MDE requires a much larger sample.
Why do I need so many visitors?
Statistical significance depends on both the effect size and the sample size. Low baseline rates and small target uplifts produce a lot of noise relative to the signal, so you need more visitors to be confident the difference is real and not chance.
How long should I run my A/B test?
Take the sample size per variant, multiply by two for both variants, and divide by your daily traffic to that page. Run at least that long (and ideally over full weeks) so you capture normal day-of-week variation before deciding.

Related free tools

A/B Test Significance Calculator

Call your A/B winner with confidence

Open tool

App Store Conversion Rate Calculator

Impressions to installs, as three rates

Open tool

Free Trial Conversion Rate Calculator

Trial-to-paid conversion rate

Open tool

A/B Test Duration Calculator

Days to run a test at your traffic

Open tool