Now returning the correct dict format.

src/deepeval/turkish_general_knowledge_task.py

@@ -1,5 +1,6 @@
 from src.deepeval.base_task import BaseTask
 from collections import defaultdict
+from src.deepeval.utils import accuracy, accuracy_standard_error
 import ast
 
 class TurkishGeneralKnowledgeTask(BaseTask):
@@ -61,9 +62,11 @@ class TurkishGeneralKnowledgeTask(BaseTask):
 
         # Print results categorized by difficulty
         for category, stats in difficulty_results.items():
-            accuracy = stats['correct'] / stats['total'] if stats['total'] > 0 else 0
-            print(f"{category.capitalize()} Accuracy: {accuracy:.2%} ({stats['correct']}/{stats['total']})")
+            calculatedAccuracy = stats['correct'] / stats['total'] if stats['total'] > 0 else 0
+            print(f"{category.capitalize()} Accuracy: {calculatedAccuracy:.2%} ({stats['correct']}/{stats['total']})")
 
         print("Results:", responses)
         print("Overall Accuracy:", true / total_count)
-        return true / total_count
+        acc = accuracy(true, total_count)
+        acc_stderr = accuracy_standard_error(acc, total_count)
+        return {"acc": acc, "acc_stderr": acc_stderr}