List your company

Mathematical Reasoning on Math Reasoning Mix Average

91.34AccuracyGPT-4 + PHP
82.437684.748887.0689.3712Apr 19, 2023

Evaluation results

MethodLinks
GPT-4 + PHPPHP=true, Prompting Strategy=Complex CoT, Decoding Strategy=greedy2023.0491.342.0716
Previous SOTAPHP=false, Prompting Strategy=Complex CoT, Decoding Strategy=greedy2023.0491.31—
GPT-4PHP=false, Prompting Strategy=Complex CoT, Decoding Strategy=greedy2023.0490.51—
GPT-3.5 Turbo + PHPPHP=true, Prompting Strategy=Complex CoT, Decoding Strategy=greedy2023.0484.162.2
GPT-3.5 TurboPHP=false, Prompting Strategy=Complex CoT, Decoding Strategy=greedy2023.0482.78—