List your company

ResearchFormerly WizWand

Deductive logical reasoning

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

ProverQA hard (test)

0Error Rate

12

Feb 27, 2026

ProntoQA (test)

2.8Error Rate

12

Feb 27, 2026

ProofWriter (test)

100ExcRate

12

Feb 27, 2026

FOLIO 203 (dev)

6.4Exclusion Rate

12

Feb 27, 2026

ProverQA OOD hard subset 500 records (test)

—

—Error Rate

0

Feb 26, 2026

ProntoQA OOD 500 records (test)

—

—ExcRate

0

Feb 26, 2026

ProofWriter 600 records (test)

—

—Exc. Rate

0

Feb 26, 2026