List your company

ResearchFormerly WizWand

OOD Quality Estimation

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Mathematical Reasoning OOD (Near-shift)

0.159Kendall Tau

12

Feb 26, 2026

Mathematical Reasoning Far-shift OOD

0.161Kendall's Tau

12

Feb 26, 2026