List your company

Mathematical Reasoning on GSM8K Zero (ACC, Output Tokens, Expense)

99.5ACCVanilla CoT
97.118497.736798.35598.9733Dec 24, 2024

Evaluation results

MethodLinks
Vanilla CoTPrompting Strategy=Vanilla CoT, Model=GPT-4o-mini2024.1299.5252.96886.79
TALE-EPPrompting Strategy=TALE-EP, Model=GPT-4o-mini2024.1298.7222.67276.12
Directly AnsweringPrompting Strategy=Directly Answering, Model=GPT-4o-mini2024.1297.2118.8591.69