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

Large Language Model Reasoning and Understanding research benchmarks · SOTA2 Research

Large Language Model Reasoning and Understanding

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Llama-3.2-3B-Instruct Evaluation Suite (test val)

37.3MMLU Pro

25

Jun 9, 2026

Popular datasets

Llama Evaluation Suite

Follow for updates

Join SOTA2 Contact