List your company

Mathematical Reasoning on Math QA

64.86AcleanAGLS
0.525617.227833.9350.6322May 26, 2025

Evaluation results

MethodLinks
AGLSModels=qwen2.5-14B2025.0564.8639.1839.591.16
AGLSModels=gpt-42025.0548.534.528.871.12
AGLSModels=gpt-4o-latest2025.0532.422.3331.080.82
AGLSModels=llama3.1-70B2025.0513.6711.6717.121.27
AGLSModels=qwen2.5-7B2025.0510.33280.640.69
AGLSModels=gemma2-27B2025.0510.33280.641.28
AGLSModels=llama3.1-8B2025.058.674.6746.120.23
AGLSModels=gemma2-9B2025.057.673.6752.150.44
AGLSModels=llama3.2-3B2025.053166.670.15