diff --git a/Evaluation/2_EvaluateTestOutput.py b/Evaluation/2_EvaluateTestOutput.py
index 5e961ec..e39af37 100644
--- a/Evaluation/2_EvaluateTestOutput.py
+++ b/Evaluation/2_EvaluateTestOutput.py
@@ -37,7 +37,7 @@
     print(send_prompt)
     while True:
         try:
-            response = openai.ChatCompletion.create(model='gpt-3.5-turbo', messages=[ {"role": "user", "content": send_prompt}], max_tokens=200, temperature=0)
+            response = openai.ChatCompletion.create(model='gpt-4', messages=[ {"role": "user", "content": send_prompt}], max_tokens=200, temperature=0)
             ret = response['choices'][0]['message']['content']
         except:
             print("Error: API call failed, will try repeating it in 10 seconds!")
diff --git a/Evaluation_babI_qa16/2_EvaluateTestOutput.py b/Evaluation_babI_qa16/2_EvaluateTestOutput.py
index a26ec3b..fc53beb 100644
--- a/Evaluation_babI_qa16/2_EvaluateTestOutput.py
+++ b/Evaluation_babI_qa16/2_EvaluateTestOutput.py
@@ -37,7 +37,7 @@
     print(send_prompt)
     while True:
         try:
-            response = openai.ChatCompletion.create(model='gpt-3.5-turbo', messages=[ {"role": "user", "content": send_prompt}], max_tokens=200, temperature=0)
+            response = openai.ChatCompletion.create(model='gpt-4', messages=[ {"role": "user", "content": send_prompt}], max_tokens=200, temperature=0)
             ret = response['choices'][0]['message']['content']
         except:
             print("Error: API call failed, will try repeating it in 10 seconds!")