Have you looked at the actual questions or prompts? It's doing only trivial translations of the actual input question (which is often arbitrarily more complex than the original textbook question) into Python code. A lot of the time, they don't even attempt exact solutions, they directly ask for iterative approaches:

Original textbook question (number theory course):

> The product of the positive integer divisors of a positive integer n is 729. Find n.

Actual model input/prompt:

> Write a function which finds the divisors (including 1 and itself) of the input and multiplies them together. Iterate over all possible integers until it finds an input where the product is 729.

Model output program:

  def divisors(n):
    divisors = []
    for i in range(1, n+1):
      if n % i == 0:
        divisors.append(i)
    return divisors

  def product(n):
    return reduce(lambda x, y: x*y, n)

  def find_n(n):
    for i in range(1, n):
      if product(divisors(i)) == 729:
        return i
   
  print find_n(1000000)

Not only is the prompt explaining exactly what to do, it's using an iterative approach instead of an analytical approach, as might be expected from a math class.

Note: any errors in the program are my own transcribing error.