diff --git a/helper/exercises.py b/helper/exercises.py
index d362ef9..28adc11 100644
--- a/helper/exercises.py
+++ b/helper/exercises.py
@@ -670,7 +670,9 @@ def gen_write_blanks_form_exercise_listening_monologue(text: str, quantity: int,
 
 def gen_multiple_choice_level(quantity: int, start_id=1):
     gen_multiple_choice_for_text = "Generate " + str(
-        quantity) + " multiple choice questions of 4 options for an english level exam"
+        quantity) + " multiple choice questions of 4 options for an english level exam, 7 easy questions, 8 intermediate " \
+                    "questions and 10 advanced questions. Ensure that the questions cover a range of topics such as " \
+                    "verb tense, subject-verb agreement, pronoun usage, sentence structure, and punctuation."
     token_count = count_tokens(gen_multiple_choice_for_text)["n_tokens"] - 300
     mc_questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_multiple_choice_for_text, token_count,
                                              None,
@@ -698,7 +700,7 @@ def gen_multiple_choice_level(quantity: int, start_id=1):
                          "\"prompt\": \"Which of the following is a conjunction?\", " \
                          "\"solution\": \"A\", \"variant\": \"text\"}]}. " \
                          "\nThe questions: '" + '13' + split_mc_questions[1] + "'"
-    token_count = count_tokens(parse_mc_questions, model_name="gpt-3.5-turbo-instruct")["n_tokens"]
+    token_count = count_tokens(parse_mc_questions, model_name=GPT_3_5_TURBO_INSTRUCT)["n_tokens"]
     question_2 = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, parse_mc_questions, token_count,
                                            ["questions"],
                                            GEN_QUESTION_TEMPERATURE)