List your company

Multiple Choice Question Answering on MMLU redux

85.11AccuracyGaC + SAFE
82.229282.977183.72584.4729Oct 17, 2025

Evaluation results

MethodLinks
GaC + SAFEEnsembling models=Qwen2.5 + EXAONE3.52025.1085.11
Qwen2.5-32BScale=32B2025.1085.06
GaCEnsembling models=Qwen2.5 + EXAONE3.52025.1084.7
EXAONE3.5-32BScale=32B2025.1082.34