A/B Test Sample Size Calculator
Work out how many visitors each variant needs before you start, so you never run a test that could not have concluded. Computed live in your browser.
How to use this
Enter the rate the page converts at today, the smallest relative improvement you would care about detecting, and your confidence and power targets. The calculator returns the visitors each variant needs to detect that effect reliably. Smaller effects and lower baselines need far more traffic, which is why chasing tiny lifts on low-traffic pages rarely pays.
Set this before launching, then read the result honestly with the significance calculator. The reasoning behind power and sample size is in statistical significance for product managers, and how to concentrate traffic where it pays is in experiment prioritization.
Built by Deepanshu Grover, a Growth Product Manager and AI builder in Paris. Runs entirely in your browser, nothing is sent anywhere. About · Get in touch