--- url: 'https://dxpr.com/hc/documentation/learn-dxpr-builder/integrations/analyzing-results' title: 'Read your A/B test results | DXPR' author: name: docs-sync url: 'https://dxpr.com/users/docs-sync' date: '2026-10-23T14:31:17+00:00' copyright: 'Copyright DXPR. All rights reserved.' type: article summary: 'Read the RL reports and decide which variant wins' tags: - 'Test variations' image: 'https://dxpr.com/themes/custom/dxpr_com/images/dxpr-share-card.jpg' published: true og: site_name: DXPR updated_time: '2026-10-23T14:31:17+0000' 'image:alt': 'DXPR, powered by Drupal: AI-powered Drupal for marketers.' schema: '@context': 'https://schema.org' '@graph': - mainEntity: { } - '@type': TechArticle headline: 'Read your A/B test results' description: 'Read the RL reports and decide which variant wins' image: '@type': ImageObject url: 'https://dxpr.com/themes/custom/dxpr_com/images/dxpr-share-card.jpg' width: '1200' height: '630' datePublished: '2026-10-23T14:31:17+0000' dateModified: '2026-10-23T14:31:17+0000' author: '@type': Organization '@id': 'https://dxpr.com/#organization' name: DXPR url: 'https://dxpr.com/' logo: '@type': ImageObject url: 'https://dxpr.com/themes/custom/dxpr_com/dxpr-logo-dark.svg' width: '1348' height: '501' publisher: '@type': Organization '@id': 'https://dxpr.com/#organization' name: DXPR url: 'https://dxpr.com/' logo: '@type': ImageObject url: 'https://dxpr.com/themes/custom/dxpr_com/dxpr-logo-dark.svg' width: '1348' height: '501' mainEntityOfPage: 'https://dxpr.com/hc/documentation/learn-dxpr-builder/integrations/analyzing-results' articleSection: 'Test variations' - '@type': WebPage '@id': 'https://dxpr.com/hc/documentation/learn-dxpr-builder/integrations/analyzing-results' description: 'Read the RL reports and decide which variant wins' breadcrumb: '@type': BreadcrumbList itemListElement: - '@type': ListItem position: 1 name: Home item: 'https://dxpr.com/' publisher: '@type': Organization '@id': 'https://dxpr.com/#organization' name: DXPR inLanguage: en --- [Help Center](/hc)/[Documentation](/hc/documentation) /[Learn DXPR Builder](/hc/documentation/learn-dxpr-builder) /[Manage the site](/hc/documentation/learn-dxpr-builder/manage) /[Test variations](/hc/documentation/learn-dxpr-builder/integrations/ab-testing-overview) # Read your A/B test results. Read the RL reports and decide which variant wins Learn DXPR BuilderManage the siteTest variations ## In this guide Related guides - [Multivariate testing](/hc/documentation/learn-dxpr-builder/integrations/multivariate-testing) See how each version of your test performs and which one is winning. You open the RL report, find your test and compare the scores of its versions. Charts over time are optional; you switch them on once in the RL settings. ## Before you start - Your role has the **View RL reports** permission. - For charts over time, **Enable event log** is on; see [Settings](#settings). ## Set up 1. Go to **Reports** > **RL: A/B Testing**(`/admin/reports/rl`). 2. Find your test in the **Experiment** column. Its name starts with the content type and the page title. 3. Click **View** in the **Operations** column. 4. Compare the **Conversion Score** of the variants. From the editor, the element's **More** menu has a shortcut: **View A/B test results** opens the same page in a new tab. Smart sort elements offer **View smart sort results**. ## What you see The overview lists every test with its totals. **Source** says `dxpr_builder` for tests made in the editor. **Last Activity** shows when its numbers last changed. The detail page has one row per variant: | Column | Meaning | |---|---| | **Variant** | the letter, or the item for smart sort | | **Impressions** | how often visitors saw it | | **Conversions** | how often the chosen action followed | | **Conversion Rate** | conversions divided by impressions | | **Conversion Score** | (conversions + 1) divided by (impressions + 2) | The table starts sorted by **Conversion Rate**; click a column to sort by it. Trust the **Conversion Score** more: 2 of 4 and 200 of 400 both make a 50% rate, but only the second is reliable, and the score shows that. With the event log on, a **Variant Performance**chart sits above the table. Up to nine variants show as lines over time; more show as a 3D landscape. **Time range**, **X-axis**, **Y-axis**and **Max variants** change what the chart shows. ## Start a test over Click **Delete** in the **Operations** column to reset a test's numbers. The test starts again from zero on the next page view. This needs the **Administer RL experiments** permission. ## Settings Find these under **Configuration** > **Web services** > **RL: A/B Testing**(`/admin/config/services/reinforcement-learning`). | Setting | What it does | Default | |---|---|---| | **Enable event log** | Records snapshots over time for the charts | off | | **Maximum event log rows** | Cron trims older snapshots above this number | 100000 | | **Line chart threshold** | Most variants shown as lines; above it the 3D chart opens first | 9 | | **Enable debug mode** | Logs the sampling scores; for short troubleshooting only | off | ## If you don't see your results - **Your test is not in the list.** Tests register when you save the page with at least two versions. Open the page in the editor and click **Save** again. - **The page says "Event logging is disabled."**Charts need the event log. Tick **Enable event log** in the RL settings. - **The page says "No data yet."** The event log is on, but nobody has seen the test since. Wait for visitors. - **Impressions stay at zero.** The site cannot reach rl.php. Check **RL: rl.php accessibility**on the status report (`/admin/reports/status`). ## What's next? [Multivariate testing for more complex experiments](/hc/documentation/learn-dxpr-builder/integrations/multivariate-testing) to continue exploring DXPR Builder.