An example from ChatGPT:
"What is the solution to sqrt(968684)+117630-0.845180" always produces the correct solution, however;
"Write a speech announcing the solution to sqrt(968684)+117630-0.845180" produces a nonsensical solution that isn't even consistent from run to run.
My assumption is the former query gets WolframAlpha'd but the latter query is GPT itself actually attempting to do the math, poorly.