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

Self-confidence estimation research benchmarks · SOTA2 Research

Self-confidence estimation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AIME hard OOD 23–25 (test)

12.9Accuracy

6

Feb 26, 2026

GSM8K easy OOD (test)

89.8Accuracy

6

Feb 26, 2026

MATH500 in-distribution (test)

78.6Accuracy

6

Feb 26, 2026

Popular datasets

GSM8K MATH AIME

Follow for updates

Join SOTA2 Contact