List your company

ResearchFormerly WizWand

Prevalence Estimation

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

ACS (American Community Survey) Out-of-Distribution

-17.27Prevalence Estimation Bias (pp)

32

Apr 24, 2026

ACS (American Community Survey) In-Distribution

-19.97Prevalence Estimation Bias (pp)

32

Apr 24, 2026

CAP Law & Crime (Belgium TV) Claude Opus 4.6 (test)

Importance-weighted estimation

-4.5Prevalence Estimation Bias (pp)

7

Apr 24, 2026

CAP Law & Crime Spain media Claude Opus 4.6 (test)

Importance-weighted estimation

-12.2Prevalence Estimation Bias (pp)

7

Apr 24, 2026

CAP Law & Crime Doc-type shift Claude Opus 4.6 (test)

-0.3Prevalence Estimation Bias (pp)

7

Apr 24, 2026

CAP Law & Crime Country shift Claude Opus 4.6 (test)

Importance-weighted estimation

0.1Prevalence Estimation Bias (pp)

7

Apr 24, 2026

CAP Law & Crime Baseline Claude Opus 4.6 (test)

Importance-weighted estimation

0.1Prevalence Estimation Bias (pp)

7

Apr 24, 2026

Comparative Agendas Project (CAP) Spain media OOD doc type 105,000-document sample

-9.8Prevalence Estimation Bias (pp)

5

Apr 24, 2026

Comparative Agendas Project (CAP) Doc-type shift 105,000-document sample (Within-calibration)

0Prevalence Estimation Bias (pp)

5

Apr 24, 2026

Comparative Agendas Project (CAP) Country shift 105,000-document sample (Within-calibration)

-0.3Prevalence Estimation Bias (pp)

5

Apr 24, 2026

Comparative Agendas Project (CAP) Baseline 105,000-document sample (in-distribution)

0.1Prevalence Estimation Bias (pp)

5

Apr 24, 2026