Evidence

Synthetic research validation evidence

Not a ranking. Metrics are not converted into one score. A cell that says not publicly located is not a claim that the vendor has no validation. Lewsearch is included because it maintains this resource. Lewsearch plus vendors already covered on lewsearch.com/compare. Additional vendors are not added until a source review is complete.

Compiled 2026-09-12 from Lewsearch compare pages that already cite each vendor's primary URL. Live vendor sites were not re-crawled for this table. Corrections: jeffrey@lewsearch.com.

JSON · CSV · Compare hub · Study records

Published validation claims by vendor. Not a composite ranking.
VendorClaimMetricn / questionsSource

Lewsearch

tabulated synthetic panel

About 10 pp MAE as shipped on 1,521 scored questions, 50 states, n=200, no extra calibration

Vendor-maintained resource includes Lewsearch. Not 1,521 independent poll fieldings. Does not validate quotes, conversion, or WTP.

MAE (percentage points)q=1521 · n=200Source

checked 2026-09-12

Lewsearch

tabulated synthetic panel

7.47 pp MAE on 404 non-electoral questions of a 460-question bank

Historical. Not the product default. Do not convert to percent accurate.

MAE (percentage points)q=404 · n=10000Source

checked 2026-09-12

Simile

enterprise simulation

7,000+ weekly evaluations; no pooled public-poll MAE located on the homepage review

Compiled from Lewsearch compare pages that cite simile.com. Volume is not MAE. A failed later fetch would not mean Simile has no validation.

evaluation volume (weekly evaluations)q=n/a · n=n/aSource

checked 2026-09-12

Aaru

enterprise simulation

Median Spearman 0.90 and 7.1 pp RMSE on 53 questions of one EY wealth study

Do not convert Spearman or RMSE into Lewsearch MAE. One study is not a pooled public-poll book.

Spearman rho; RMSE (correlation; percentage points)q=53 · n=n/aSource

checked 2026-09-12

Synthetic Users

qualitative synthetic interviews

85-92% synthetic-organic thematic parity

Parity is not MAE. Pricing cited on compare pages: $2-$60 per interview.

thematic parity (percent overlap)q=n/a · n=n/aSource

checked 2026-09-12

Minds

synthetic consumer insights

80 to 95 percent agreement on a comparison-hub post; 85 to 95 percent on a FAQ; methodology says no universal percentage

Vendor pages disagree on the range. Do not convert agreement percent to MAE. Pricing is on getminds.ai/pricing.

agreement range (percent agreement)q=n/a · n=n/aSource

checked 2026-09-12

FishDog (formerly Ditto on some research pages)

census-grounded personas

92% overlap with traditional focus groups across 50+ parallel studies, on a FishDog-authored market-map post

Self-authored post is not independent reproduction. $50,000-$75,000/yr appears on that post, not as a homepage rate card. Do not invert 92% into MAE.

focus-group overlap (percent overlap)q=n/a · n=n/aSource

checked 2026-09-12