Is your A/B test ready to call?
Enter the sessions and orders for each test group. You'll see each group's conversion rate, the chance that B converts better than A, and — if you add how many days the test has run — about how many more days it needs. Everything is calculated in your browser; nothing you enter is sent or saved.
Result
| Conversion rate | A: 2.00% (1.6%–2.4%) | B: 2.60% (2.2%–3.1%) |
|---|---|---|
| Chance B converts better | 98% | |
| Verdict | B is likely converting better (98% chance). | |
| Why | Needs at least 100 sessions in each group and 10 orders in total. A result is called at 95% chance or more. | |
The range in brackets is where the true rate most likely sits, given your traffic so far.
The difference in conversion is unlikely to be chance. Before applying B, check what it does to revenue and profit — more orders can still mean less money.
Conversion is only half the answer. This calculator compares conversion rates. Comparing net sales, discounts and profit for each test group needs your store's order data — Upshot does that inside your store for your Rollouts experiments (estimated for discount tests).
Questions
- How long should I run an A/B test?
- Until both groups have enough sessions and orders to show a real difference — usually at least one full week, so weekday and weekend shoppers are both counted. Add “Days running” above and the calculator estimates how many more days you need at your current traffic.
- The conversion rates look the same. What now?
- If the verdict says “No clear difference after enough traffic,” the change probably doesn't matter much for conversion. You can end the test. Before you do, compare revenue per session — a variant can convert the same and still earn more or less per order.
- Why don't I see a percentage yet?
- While the verdict is “Too early to call,” there isn't enough data for the percentage to mean much, so it isn't shown. It appears once each group passes the minimum number of sessions and orders.
- Are my numbers saved?
- No. The calculation runs in your browser. Nothing you enter is sent to a server or stored.
Run experiments in Rollouts?
Upshot shows each test group's conversion, revenue and profit side by side, gives the same plain-language verdict as this calculator, and logs store changes on your Analytics charts.
Free to install. Revenue and profit by test group come with a 14-day free trial.
Independent tool — not affiliated with or endorsed by Shopify. “Shopify” and “Rollouts” are used only to describe compatibility.