I would assume a smaller model trained specifically to produce code based on natural language input would perform at least just as well, which would already be better given the smaller size / probably lower training resource requirements. This is of course, as already said, an assumption. But generalizing typically comes at a cost, there is no reason why this wouldn't apply to LLMs, it even applies to humans.

Does it? All of the latest frontier models that have made technical details publicly available are using MoE; smaller specialized units that work together.