diff --git a/evaluation/benchmarks/mint/tasks/reasoning.py b/evaluation/benchmarks/mint/tasks/reasoning.py
index 08cf320c35..64fb18a6b0 100644
--- a/evaluation/benchmarks/mint/tasks/reasoning.py
+++ b/evaluation/benchmarks/mint/tasks/reasoning.py
@@ -307,7 +307,7 @@ class TheoremqaTask(Task):
 
         # Converting the string answer to a number/list/bool/option
         try:
-            prediction = eval(prediction)
+            prediction = ast.literal_eval(prediction)
         except Exception:
             LOGGER.warning(
                 f'[TASK] Failed to convert the answer: {prediction}\n{traceback.format_exc()}'