Qwen2.5 32B Instruct

ARC-C benchmark evaluation

BBH benchmark evaluation

GPQA benchmark evaluation

GSM8K benchmark evaluation

HellaSwag benchmark evaluation

HumanEval benchmark evaluation

HumanEval+ benchmark evaluation

MATH benchmark evaluation

MBPP benchmark evaluation

MBPP+ benchmark evaluation

MMLU benchmark evaluation

MMLU-Pro benchmark evaluation

MMLU-redux benchmark evaluation

MMLU-STEM benchmark evaluation

MultiPL-E benchmark evaluation

TheoremQA benchmark evaluation

TruthfulQA benchmark evaluation

Winogrande benchmark evaluation