Six weeks of data. The webview converted less than half as well.
The longest high-volume window in the portfolio: 42 days, 54,598 randomized visitors. Escaped traffic converted +125% better and produced +142% more revenue per visitor — at z = 12.5, one of the most decisive results we've measured.
This brand sells premium everyday-carry leather goods — $90+ average orders where shoppers compare, hesitate, and come back later. A checkout that can't autofill a saved card and a session that evaporates on app-switch are worst-case conditions for that buying pattern.
Over six weeks the gap never closed: escaped visitors converted at 2.56% vs 1.14% for the in-app-browser control (+125%), and generated $2.43 per visitor vs $1.01 (+142%). No outlier orders on either arm.
Long windows answer the objection short tests can't: this wasn't a hot week or a lucky drop. Six weeks of paid and organic Instagram traffic, and the control never once looked like the winning arm.
After the test: The measured window closed in late June 2026 with the result above.
| Arm | Visitors | Orders | CVR | Rev / visitor |
|---|---|---|---|---|
| A · escaped | 24,999 | 639 | 2.56% | $2.43 |
| B · control | 29,599 | 337 | 1.14% | $1.01 |
Brand anonymized. Arm sizes are uneven (25.0K vs 29.6K) because escape stayed on outside strict test hours at the window edges; conversion and revenue-per-visitor are per-capita and unaffected by arm size.
Run this exact test on your traffic.
One script tag, 60-second install. Randomized 50/50 from the first visitor — in 7–14 days this page is your data.