Large Language Models (LLMs) have garnered remarkable advancements across diverse code-related tasks, known as Code LLMs, particularly in code generation that generates source code with LLM from natural language descriptions. This burgeoning field has captured significant interest from both academic researchers and industry professionals due to its practical significance in software development, e.g., GitHub Copilot. Despite the active exploration of LLMs for a variety of code tasks, either from the perspective of natural language processing (NLP) or software engineering (SE) or both, there isResearch goal: How does the F1-score of Llama3-70B compare to Codestral-7B on the CodeT5 benchmark for code understanding tasks (e.g., clone detection) when both models are fine-tuned on security-specific code corpora versus general code corpora?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.6/10.