This paper explores the integration of large language models (LLMs) into building energy modeling (BEM), focusing on the fusion of LLMs with EnergyPlus. The authors conduct a literature review to highlight the growing trend of LLMs in engineering modeling and their potential applications in BEM. They outline six key areas where LLMs can enhance BEM: simulation input generation, output analysis and visualization, error analysis, co-simulation, knowledge extraction and training, and simulation optimization. Three case studies are presented to demonstrate the effectiveness of LLMs in automating and optimizing BEM tasks. The studies highlight the importance of selecting appropriate LLM techniques, such as prompt engineering, retrieval-augmented generation, and multi-agent systems, to optimize performance and reduce engineering efforts. The paper also discusses challenges such as computational demands and self-consistency issues, and suggests future research directions, including the development of domain-specific LLMs like "BEMGPT." Overall, the integration of LLMs in BEM is seen as a transformative approach to advancing sustainable building practices and energy efficiency.This paper explores the integration of large language models (LLMs) into building energy modeling (BEM), focusing on the fusion of LLMs with EnergyPlus. The authors conduct a literature review to highlight the growing trend of LLMs in engineering modeling and their potential applications in BEM. They outline six key areas where LLMs can enhance BEM: simulation input generation, output analysis and visualization, error analysis, co-simulation, knowledge extraction and training, and simulation optimization. Three case studies are presented to demonstrate the effectiveness of LLMs in automating and optimizing BEM tasks. The studies highlight the importance of selecting appropriate LLM techniques, such as prompt engineering, retrieval-augmented generation, and multi-agent systems, to optimize performance and reduce engineering efforts. The paper also discusses challenges such as computational demands and self-consistency issues, and suggests future research directions, including the development of domain-specific LLMs like "BEMGPT." Overall, the integration of LLMs in BEM is seen as a transformative approach to advancing sustainable building practices and energy efficiency.