Not for generating it, because the more it looks like prose the more the LLM's output will be influenced by all the prose it's ingested.
It also does a reasonable job of generating working COBOL. I had to fix up just a few errors in the data definitions as the llm generated badly sized data members, but it was pretty smooth. Much smoother than my experiences with llm's and Python. What a crap shoot Python is with llm's...