How long should my A/B test run?
Find out how many days your A/B test needs from your daily traffic, conversion rate and the lift you want to detect, rounded to full weeks. Free.
How it works
The calculator works out the sample size each version needs, then divides by the visitors per day that enter the test.
It rounds up to whole weeks, because people behave differently on weekends, and a test that runs Monday to Thursday only measures weekday visitors. It also flags tests that would take longer than six weeks: by then cookies expire, seasons change, and the result gets less reliable. If yours is that long, test a bolder change or a page with more traffic.
Example: 800 visitors a day to your pricing page, all in the test, a 4% conversion rate and a 20% lift to detect needs about 10,300 visitors per version. That's 26 days, rounded up to 4 weeks.
Questions people ask
How long should you run an A/B test?+
Long enough to reach your planned sample size, and never less than one full week so every day of the week is counted. Most tests on small and mid-size sites need two to six weeks.
Can I stop my test early if it's clearly winning?+
Not safely with standard statistics. Checking daily and stopping at the first significant result makes false winners far more likely. Set the duration up front, or use a method designed for continuous monitoring.
What if my test would take months?+
Test something bolder so the expected lift is bigger, test a page with more traffic, or test upstream with ads where traffic is cheaper to buy.
Learn more
More free tools
Want the tests run for you?
AI agents read your analytics and payments, find where you lose the most money, build the fix and test it. Every test is judged on revenue, not clicks. Plans from $29 a month.