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

General Reasoning Average research benchmarks · SOTA2 Research

General Reasoning Average

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Official Instruct Model

44.81Average (%)

17

Jun 2, 2026

Aggregate OBQA, CSQA, SIQA, ARC, MMLU, GSM8K-MC, AQUA

86.21Average Accuracy

14

Apr 8, 2026

Popular datasets

Aggregate PostTrainBench

Follow for updates

Join SOTA2 Contact