The field of software engineering and coding has undergone a significant transformation. The integration of large language models (LLMs), such as ChatGPT, into software development workflows has changed how developers at all skill levels approach coding tasks. Leveraging the capabilities of LLMs, developers can now implement functionalities, fix bugs, and address reviewers’ comments more efficiently. However, prior research shows that the effectiveness of LLM-generated code is heavily influenced by the prompting strategy used. Furthermore, generating code at the class level is significantly more complex than at the method level, as it requires maintaining consistency across multiple methods and managing class state. Therefore, in this study, we evaluate the impact of four prompting strategies (i.e., Zero-Shot, Few-Shot, Chain-of-Thought (CoT), and CoT Few-Shot) on GPT’s performance in generating class-level code. We assess both the functional correctness and the quality characteristics of the generated code. To better understand how errors differ by prompting strategy, we conduct a qualitative analysis of the generated code for test cases that fail. We find that strategies incorporating more contextual guidance (Few-Shot, CoT, and CoT Few-Shot) outperform Zero-Shot prompting by up to 25% in functional correctness, 31% in BLEU-3 score, and 50% in ROUGE-L, while also producing code that is more readable and maintainable. Also, our results indicate that procedural logic and control flow errors are the most prominent, accounting for 25% of all errors. We believe our study provides valuable insights to guide future research in developing techniques and tools that enhance the quality and reliability of LLM-generated code for complex software development tasks.