A/B Test Calculator
Find out how many visitors you need and how long to run your A/B test to get statistically significant results.
Your current baseline conversion rate
Relative improvement you want to detect (e.g. 20% = 3% to 3.6%)
Average daily visitors to the page being tested
Confidence level for your results
Total number of versions including original
Ready to run this test?
CROTool lets you build, publish, and track A/B tests — free. No code needed.
Start testing freeFrequently Asked Questions
How long should I run an A/B test?
The duration depends on your traffic volume, baseline conversion rate, and the minimum effect you want to detect. Most tests need at least 1-2 weeks to reach statistical significance. Never stop a test early just because one variant looks like a winner — that leads to false positives.
What sample size do I need for an A/B test?
Sample size depends on your current conversion rate and how small an improvement you want to detect. Smaller effects require larger samples. A page converting at 3% that wants to detect a 20% relative lift (3% to 3.6%) needs roughly 7,000 visitors per variant at 95% significance.
What statistical significance should I use?
95% is the industry standard and works for most tests. Use 90% when you need faster results and can tolerate a higher false positive rate. Use 99% for high-stakes tests like pricing or checkout flow changes where a wrong decision is costly.
Does adding more variants increase the test duration?
Yes. Each variant needs its own sample of visitors, so adding variants splits your traffic further. A test with 3 variants takes roughly 50% longer than a test with 2 variants, assuming the same daily traffic. Stick to 2 variants unless you have strong reasons to test more.