List your company

ResearchFormerly WizWand

Answer Verification

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

0.913AUROC

43

Mar 18, 2026

91.05AUROC

22

Mar 5, 2026

0.965AUROC

12

Mar 5, 2026

Omni-MATH terminal answers

0.929AUROC

11

Mar 5, 2026

AIME terminal answers

98.22AUROC

11

Mar 5, 2026

OlympiadBench terminal answers

0.955AUROC

11

Mar 5, 2026

0.859AUROC

11

Mar 5, 2026

89.46AUROC

11

Mar 5, 2026