Access GoodUI through our MCP serverNEW Learn more Access GoodUI through our MCP serverNEW

All Latest 650 A/B Tests

New 10 tests added since your last visit

MOST RECENT TESTS

Test #143 on Vivareal.com.br by Rodrigo MauésRodrigo Maués Jan 14, 2018 Desktop Listing X.X% Leads

Rodrigo Tested Pattern #56: Hover Button On Vivareal.com.br

Pattern #56: Hover Button - Variant A
Pattern #56: Hover Button - Variant B
Total Sample: 2,594,182 • Statistical Power at 5% MDE: 99.9%

Which A Or B Actually Wins? Find Out Before You Test.

Members see every test result — the winners, the flat ones, and the losers — along with exact effects and sample sizes. Use it to estimate your tests and prioritize by probability, not gut feel. Start every experiment with the odds on your side.

Test #133 on Bing.com by Ronny KohaviRonny Kohavi Dec 13, 2017 Desktop Mobile Listing X.X% Revenue

Ronny Tested Pattern #43: Long Titles On Bing.com

Pattern #43: Long Titles - Variant A
Pattern #43: Long Titles - Variant B

In 2012 a Microsoft employee working on Bing had an idea about changing the way the search engine displayed ad headlines. Developing it wouldn’t require much effort—just a few days of an engineer’s time—but it was one of hundreds of ideas proposed, and the program managers deemed it a low priority. So it languished for more than six months, until an engineer, who saw that the cost of writing the code for it would be small, launched a simple online controlled experiment—an A/B test—to assess its impact. Within hours the new headline variation was producing abnormally high revenue, triggering a “too good to be true” alert.

HBR, September–October 2017 Issue, https://hbr.org/2017/09/the-surprising-power-of-online-experiments

Note: This experiment was a solid success and replicated multiple times over a period of months. It worked at Bing and had a profound influence. The only reason why we atributed a 0.25 point (a "Maybe") was because we don't have the exact sample size and conversion data.

 

Test #127 on Glass.net by Mark FreedleMark Freedle Nov 23, 2017 Desktop Mobile Listing X.X% Leads

Mark Tested Pattern #42: Countdown Timer On Glass.net

Pattern #42: Countdown Timer - Variant A
Pattern #42: Countdown Timer - Variant B
Total Sample: 61,034 • Statistical Power at 5% MDE: 23.7%

Test #119 on Vivareal.com.br by Rodrigo MauésRodrigo Maués Nov 01, 2017 Desktop Listing X.X% Leads

Rodrigo Tested Pattern #36: Fewer Or More Results On Vivareal.com.br

Pattern #36: Fewer Or More Results - Variant A
Pattern #36: Fewer Or More Results - Variant B
Total Sample: 2,452,622 • Statistical Power at 5% MDE: 99.9%

Test #120 on Vivareal.com.br by Rodrigo MauésRodrigo Maués Nov 01, 2017 Desktop Listing X.X% Leads

Rodrigo Tested Pattern #37: List Or Grid View On Vivareal.com.br

Pattern #37: List Or Grid View - Variant A
Pattern #37: List Or Grid View - Variant B
Total Sample: 1,847,933 • Statistical Power at 5% MDE: 99.9%

Test #114 on Akademiafotografii.p... by Grzegorz JancewiczGrzegorz Jancewicz Sep 01, 2017 Desktop Listing X.X% Leads

Grzegorz Tested Pattern #32: Condensed List On Akademiafotografii.p...

Pattern #32: Condensed List - Variant A
Pattern #32: Condensed List - Variant B
Total Sample: 3,363 • Statistical Power at 5% MDE: 5.3%

Test #113 on Vivareal.com.br by Rodrigo MauésRodrigo Maués Sep 01, 2017 Desktop Listing X.X% Leads

Rodrigo Tested Pattern #31: Instant Filter Results On Vivareal.com.br

Pattern #31: Instant Filter Results - Variant A
Pattern #31: Instant Filter Results - Variant B
Total Sample: 238,851 • Statistical Power at 5% MDE: 99.7%

Test #97 on 3dhubs.com by Rob DraaijerRob Draaijer May 03, 2017 Desktop Mobile Listing X.X% Leads

Rob Tested Pattern #24: Visible Availability On 3dhubs.com

Pattern #24: Visible Availability - Variant A
Pattern #24: Visible Availability - Variant B
Total Sample: 13,441 • Statistical Power at 5% MDE: 14.5%

Test #91 on 3dhubs.com by Rob DraaijerRob Draaijer Jan 01, 2017 Desktop Listing X.X% Leads

Rob Tested Pattern #9: Multiple Steps On 3dhubs.com

Pattern #9: Multiple Steps - Variant A
Pattern #9: Multiple Steps - Variant B

In this experiment, a long form with multiple steps was broken down into a progressive interaction form. In the B variant, as users would complete particular steps, new ones would be communicated subtly and finally come into full view.

Total Sample: 54,916 • Statistical Power at 5% MDE: 54.3%

Test #21 on Findsomeone.co.nz by Daniel BridgesDaniel Bridges Jan 01, 2016 Desktop Mobile Listing X.X% Signups

Daniel Tested Pattern #25: Nagging Results On Findsomeone.co.nz

Pattern #25: Nagging Results - Variant A
Pattern #25: Nagging Results - Variant B
Total Sample: 55,182 • Statistical Power at 5% MDE: 10.6%