> Source: https://tryordinary.com/blog/stop-a-losing-test

A/B testing

# Stop — it's losing: a clear call on A/B tests that won't recover

October 16, 2026 · Updated November 1, 2026

## Overview

[Ordinary's Shopify A/B testing](/solutions/ab-testing)
now tells you when to stop an A/B test that's losing: the verdict reads
Stop — it's losing, names the version, and gives the chance it still
beats your original. When you run several tests at once, it also names
the best version of each, weighed together.

Stop — it's losing Demo data        Stop — it's losing

## Stop sending shoppers to the weaker page

### End a loser in days, not months

Every extra day a losing version runs sends real shoppers, and real revenue, to the weaker page. A clear stop call lets you end it, put your next idea live, and run more tests a quarter on the same traffic, even on a store without huge traffic.

### Which verdict you'll see, and when

While a test runs, its verdict tells you to ship a clear winner, to stop a clear loser, or to keep running when it's too close. Once you've ended a test, a version that lost reads Keep control, so a finished test is never told to stop.

[Read the guide: reading your test results](https://help.tryordinary.com/features/experiments)

Overlapping tests

## The best version of each test, weighed together

### Best so far, when tests overlap

Running more than one test on the same pages? The overlap card on each test opens with Best so far: one chip per test naming the version that's ahead, marked Clear, Early sign, Too close or Too early.

[More on running several tests side by side](/blog/ab-testing-reach-rate)

Best so farDemo data

### The winning pairing, shaded green

Early sign means the results point clearly one way before they're certain. When every test has a call, the winning pairing is shaded green, so you know which to keep while the tests finish.

### Each test's result inside the other's groups

If a change only works next to one version of another test, the table shows it, so you can decide the two together.

Also in this release

## Find any product, order or customer as you type

### Search right on top of your tables

Products, Orders and Customers now have a search box on top of the table, so you can find any product, order or customer as you type. Every column on the Products list sorts with a click.

## Available now

The stop verdict is live on **every plan**, and so are
search and sorting on your tables. Best so far appears on every plan
whenever two or more of your tests overlap; building more than one
test in Ordinary is on the **Starter plan and above**.

[Connect your store](https://apps.shopify.com/ordinary-attribution-ab-testing) [Compare plans](/pricing)        Keep reading

## More from the blog

[November 6, 2026 Connect Ordinary to Claude or ChatGPT and ask your store what's working Connect your Shopify store to Claude or ChatGPT through Ordinary and ask about sales, Meta and Google Ads, cohorts and retention, answered from your numbers.](/blog/connect-shopify-to-claude-and-chatgpt)[October 30, 2026 A GA4 events report by channel: your own events next to the orders each channel drives Ordinary's Marketing Mix now shows your GA4 custom events by channel for Shopify stores, beside each channel's orders, plus a directional read on A/B tests.](/blog/ga4-events-by-channel)[October 23, 2026 Product variants: what every size, colour and pack sells and earns See what your Shopify product variants sell and earn: units, revenue and margin by size, colour and pack, which pages sell each one, and who buys again.](/blog/product-variants)

## Stop paying for the page that's losing.

Connect your Shopify store and run A/B tests scored on your real revenue, with a clear call on when to ship and when to stop.

[Connect your store](https://apps.shopify.com/ordinary-attribution-ab-testing)
