A/B test significance calculator
Enter the visitors and conversions for each variant. See the conversion rates, the relative uplift, the p-value from a two-proportion z-test, and a clear verdict on whether the difference is statistically significant. Everything is computed in your browser.
Variant A (control)
Rate A —
Variant B (test)
Rate B —
Confidence level
Test type
Two-sided checks if B differs from A (better or worse). One-sided only checks if B is better — use it only if you decided the direction in advance.
Rate A—
Rate B—
Relative uplift—
p-value—
Everything runs in your browser. No upload, no sign-up.
How it works
STEP 1
Enter your numbers
Type visitors and conversions for the control (A) and the variant (B). Conversions can be anything you count: sign-ups, sales, clicks.
STEP 2
Pick your confidence
Choose a confidence level (90, 95 or 99%) and whether your test is one-sided or two-sided. 95% two-sided is the common default.
STEP 3
Read the verdict
Get conversion rates, the relative uplift, the p-value and a plain-English answer on whether B truly beat A — or if it is just noise.