The question you tested

Once your traditional test has been running, its report brings together the traffic, conversions, and statistical evidence you need to understand how each variation is performing.

A traditional test is built around comparison. The base and each variation are measured against the same goal so you can answer two questions:

1. Which experience is performing better?
2. Is there enough evidence to trust that difference?

For this lesson, we’ll use a simple CTA copy test to practice reading the report.

The test compares the original “Learn more” CTA with a new “Sign up today” variation.

Before we answer it, let’s get familiar with what you can find in the report.

What's in the report?

A traditional test report brings together the test result and the supporting context you can use to understand it.

You’ll typically see these key areas:

Here’s a full traditional test report so you can see how the main sections fit together before we look at them more closely.

You don’t need to interpret everything at once. For a traditional test, use this sequence:

1. See which variation is ahead
2. Check whether there’s enough evidence to trust the difference
3. Use the rest of the report for context
4. Decide what to do next

See which variation is ahead

Start with the Variations table. It gives you the clearest view of how each experience is performing against the selected goal.

For each variation, you can see:

In our CTA test example, "Sign up today" is ahead so far.

But notice the Highlights section still says "Waiting for Stat. Sig".

A higher conversion rate tells you which variation is ahead so far. It doesn’t tell you whether that lead is strong enough to trust.

That’s where statistical significance comes in.

Check whether the difference is trustworthy

In a traditional test, Optimize compares each variation with the base and estimates how reliable the observed difference appears to be.

Higher statistical significance means there’s stronger evidence that the performance difference reflects a real effect rather than normal fluctuation.

That evidence depends on more than conversion rate alone:

So even though "Sign up today" is currently converting at a higher rate, there may not yet be enough evidence to confidently call it the winner.

When there's enough evidence

When the test reaches high statistical significance, Optimize can identify a winning variation. Until then, treat an early lead as just that — an early lead.

Explore the rest of the report

Once you understand which variation is ahead and how strong the evidence is, use the rest of the report to understand the result in more detail.

Audience insights

Audience insights show how the variations performed across available visitor signals.

For example, you might see performance broken down by traffic source, device, or other visitor attributes.

These patterns can help you generate new hypotheses. Maybe "Sign up today" performed particularly well for visitors arriving from paid search, for example.

Treat these insights as additional context rather than a replacement for the overall test result.

Account engagement

If account-level information is available, the report can also show how known accounts engaged with the optimization.

Use this when account behavior matters to your business or when company-level activity adds useful context to the result.

Performance over time

The performance chart shows how conversion rates changed throughout the test.

Use it to understand the shape of the result:

• Did "Sign up today" stay ahead consistently?
• Did performance change during the test?
• Did the difference emerge gradually or suddenly?

The headline result tells you where the test landed. The chart helps you see how it got there.

Traffic allocation over time

The traffic allocation chart shows how test traffic was split between the base and variation over time.

In this example, traffic stays close to a 50/50 split throughout the test.

The stacked chart shows the percentage of sessions assigned to each experience, while the bars below show the total number of sessions recorded during each time period.

For a traditional test, this allocation follows the traffic split you configured so each experience can collect enough data for comparison.

Decide what to do next

Once you know what’s ahead, how strong the evidence is, and what context surrounds the result, decide what the evidence supports.

You might:

Each result should help inform what you optimize next.

Ready to keep going?

Continue to the next lesson where you’ll learn how to interpret manual personalization results, where the report looks familiar but the variations aren’t competing to find one overall winner.