Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Human-Metric Correlation research benchmarks · SOTA2 Research

Human-Metric Correlation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

CoGym (Out-of-Distribution)

0.365Kendall's Tau

9

Feb 26, 2026

RealHumanEval (Out-of-Distribution)

0.16Kendall's Tau

9

Feb 26, 2026

EvalGen Out-of-Distribution

0.382Kendall's Tau

9

Feb 26, 2026

HelpSteer2 (In-Distribution)

0.342Kendall's Tau

9

Feb 26, 2026

SimpEval In-Distribution

0.321Kendall's Tau

9

Feb 26, 2026

Popular datasets

SIMPEVAL HelpSteer EvalGen RealHumanEval CoGym

Follow for updates

Join SOTA2 Contact