A/B Test Sample Size Calculator
Plan your split test before you launch it: how many visitors each variant needs to reliably detect the uplift you care about.
%
%
Relative — you'd detect a move to 5.50%.
Confidence level
Statistical power
Visitors per variant
31,243
Total visitors
62,486
Estimated duration
32 days
Run the test for whole weeks where possible, and don't stop early just because the result looks significant — peeking inflates false positives.
How it works
Enter your baseline conversion rate, the minimum uplift you want to detect and your desired significance and power. The calculator tells you how many visitors you need per variant and how long the test will take at your current traffic.