This thesis evaluates Large Language Models (LLMs) using the Chain-of-Thought (CoT) prompting architecture. It employs Iterative Chain-of-Thought (Iter CoT) for analysis, utilizing various LLMs including Alpaca LoRA 13B and 30B. Results show improved accuracy with Iter CoT, notably with Alpaca LoRA 13B, outperforming ChatGPT models. - View it on GitHub