Maaz Zindani

Loading the index…

↑↓ move↵ openesc close3993 pages

Free tool · Business and sellers

Conversion rate calculator

Find your conversion rate from conversions and visitors, see how many visitors a target needs, compare two versions of a page with a significance test, or size an A/B test before you start. Every formula is shown with your own numbers.

  • Free
  • No sign-up
  • Runs in your browser

By Maaz Zindani · Updated

What do you want?
Conversion rate

3.00%45 conversions from 1,500 visitors

  • 1 conversion per 33.3 visitors
  • 97.00% did not convert
Conversions
45
Visitors
1,500
Did not convert
1,455
Visitors per conversion
33.3

Formula: conversion rate = conversions ÷ visitors × 100

Your numbers: 45 ÷ 1,500 × 100 = 3.0000%

Results are estimates from the numbers you enter, not guarantees.

How to use the Conversion Rate Calculator

  1. Choose what you want: Conversion rate, Visitors for X conversions, Compare A and B or Visitors for an A/B test.
  2. For a rate, enter the Conversions and the Visitors. For visitors needed, enter the Conversions wanted and the Conversion rate (%).
  3. To compare two versions, enter the conversions and visitors of Version A and Version B and pick a Confidence level. To size a test, enter the Current conversion rate (%) and the Change to detect.
  4. Read the answer, the chips and the formula with your numbers under the result.

How do I calculate conversion rate?

Conversion rate is the share of visitors who do what you wanted, such as buying, signing up or filling in a form: conversion rate = conversions ÷ visitors × 100. If 45 of 1,500 visitors convert, the rate is 45 ÷ 1,500 × 100 = 3.00%, which is one conversion for every 33.3 visitors. The tool shows the people who did not convert as well, so you can see both sides of the figure.

Choose the denominator once and keep it. Visitors, sessions and users give different rates for the same traffic, so a rate only compares fairly with another rate measured the same way. The tool takes whole numbers for both counts and refuses a result where conversions are higher than visitors.

To plan traffic, switch to Visitors for X conversions. The visitors you need are conversions wanted ÷ (conversion rate ÷ 100), rounded up. Fifty conversions at a 2.5% rate need 50 ÷ 0.025 = 2,000 visitors. This is an average, so a real campaign can land above or below it.

How do I calculate uplift, and is my A/B test result statistically significant?

Uplift can be quoted two ways. The difference in percentage points is rate B minus rate A, and the relative uplift is that difference divided by rate A. With 120 conversions from 4,000 visitors on version A (3.00%) and 156 from 4,000 on version B (3.90%), B is 0.90 points higher, which is a 30.00% relative uplift. Always say which one you mean, because a "30% lift" and a 0.9 point lift describe the same result.

To judge whether the gap could be chance, the tool runs a pooled two-proportion z-test, the large-sample test for comparing two proportions described in the NIST/SEMATECH e-Handbook of Statistical Methods. It pools both versions into one rate (276 ÷ 8,000 = 3.45%), divides the difference by its standard error to get z = 2.205, and finds the two-sided p-value, 0.0274. That is below the 0.05 cut-off for 95% confidence, so the result is significant at 95% but not at 99%, where the cut-off is 0.01. The tool also shows a confidence interval for the difference: here 0.10 to 1.70 points.

A significant result means the difference is unlikely to be chance alone. It does not say the change is large, or that it will repeat. Decide the number of visitors before you start, and read the result once you reach it: stopping as soon as p dips below the cut-off makes false alarms more likely. With very few conversions the normal approximation is rough, and the tool warns you when a version has fewer than 10 conversions or fewer than 10 non-conversions.

What is a good conversion rate, and how many visitors do I need?

There is no single good conversion rate. It depends on what you ask people to do, the price, where the traffic comes from and how long the decision takes, so this page gives no benchmark and publishes none. Compare your rate with your own earlier results, and with sources that measure the same action in your own field.

For an A/B test, Visitors for an A/B test gives the visitors each version needs. It uses the standard normal-approximation formula: n = (zα/2 √(2 p̄ q̄) + zpower √(p₁q₁ + p₂q₂))² ÷ (p₂ − p₁)², where p₁ is your current rate, p₂ the rate you hope to detect, p̄ their average and q = 1 − p. To detect 3% becoming 3.6% (a 20% relative change) at 95% confidence and 80% power, you need 13,914 visitors per version, or 27,828 in all.

Halving the change you want to detect roughly quadruples the visitors, because n grows with 1 ÷ (p₂ − p₁)². Higher confidence and higher power also raise it. The calculation assumes two equal groups, a two-sided test and a sample size fixed in advance. If you cannot reach it, aim for a bigger change or accept that the test will only detect large effects.

Use it with

Questions

How do I calculate conversion rate?

Divide conversions by visitors and multiply by 100. 45 conversions from 1,500 visitors is 45 ÷ 1,500 × 100 = 3.00%.

What is a good conversion rate?

It depends on the action, the price, the traffic source and your industry, so this tool gives no benchmark. Compare your rate with your own history and with sources for your field.

How do I calculate uplift between two variants?

Percentage points: rate B minus rate A. Relative uplift: that difference divided by rate A. 3.00% to 3.90% is 0.90 points, or a 30.00% relative uplift.

Is my A/B test result statistically significant?

The tool runs a pooled two-proportion z-test. If the two-sided p-value is below the cut-off for your confidence level (0.05 for 95%), the result is significant. 120 of 4,000 against 156 of 4,000 gives p = 0.0274, significant at 95% but not at 99%.

How many visitors do I need for an A/B test?

It depends on your current rate, the smallest change you want to detect, the confidence and the power. To detect 3% becoming 3.6% at 95% confidence and 80% power you need 13,914 visitors per version.

How many visitors do I need to get 50 conversions?

Divide the conversions by the conversion rate. At 2.5%, 50 ÷ 0.025 = 2,000 visitors, as an average.

How this page was made: the tool's results are computed in your browser by the code on this page, using the sources listed above; the explanations were drafted with AI help and checked against the tool's own output.