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

Step-level error discrimination research benchmarks · SOTA2 Research

Step-level error discrimination

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MATH and GSM8k (test)

0.762AUROC (Step-level Error Discrimination)

4

May 11, 2026

Popular datasets

Follow for updates

Join SOTA2 Contact