A/B Test Significance Calculator
Enter visitors and conversions for two variants to see each rate, the relative lift, the p-value, and whether the difference is significant at 95 percent confidence.
Your numbers
Results update live
Variant A rate
10.00%
Conversions / visitors
Variant B rate
12.00%
Conversions / visitors
Relative lift (B vs A)
+20.0%
Significance
Significant at 95%
p-value 0.0432
Our Pick
HubSpot
Run and track landing page tests without wiring up your own significance math each time.
How this is calculated
- Each rate = conversions / visitors.
- Relative lift = (rate B - rate A) / rate A x 100.
- A two-proportion z-test with the pooled proportion gives the z-score; the p-value is two-tailed.
- The result is called significant when the p-value is below 0.05.
This is a fixed-horizon test, so decide your sample size before you start and avoid stopping early the moment it crosses the line. Evan Miller's writing on how not to run an A/B test explains why peeking inflates false positives, and his sample size calculator helps you plan the horizon.
Frequently asked questions
What does the p-value mean here?
It is the probability of seeing a difference this large, or larger, if the two variants actually performed the same. A p-value below 0.05 is the common bar for calling a result significant at 95 percent confidence.
Which test is this?
A two-proportion z-test using the pooled proportion, two-tailed. It is the standard quick check for comparing two conversion rates with reasonably sized samples.
Can I stop the test as soon as it goes significant?
No, and this is the most common way people fool themselves. This is a fixed-horizon test. If you peek repeatedly and stop the moment it crosses 0.05, your real false-positive rate is much higher than 5 percent. Decide the sample size first, then look.