This study aims to improve financial education nationwide. Using a natural language processing approach, the researcher converted state financial literacy standards and the National Standards for Personal Financial Education developed by the Council for Economic Education (CEE) into machine-readable formats and applied OpenAI's text-embedding-ada-002 model to calculate cosine similarity scores between state and national standards. A random sample of 100 scores was manually inspected, yielding a precision rate of 85-96% through a 95% confidence interval. Results show significant variation in alignment across states and subjects, with categories like investing and managing credit being the most underrepresented. This scalable, semi-automated procedure offers a replicable framework for curriculum writers and evaluators to find specific gaps in the material, allowing them to improve financial education.