fix result

evaluator.py

@@ -220,20 +220,21 @@ def aggregate_scores(b: list[int], t: list[int]):
 
 
 def generate_behavioral_score(eval_array):
+    print(eval_array)
     scores = []
 
     for eval in eval_array:
         fail_score = 0
         success_score = 0
 
-        if eval[0]["label"] == "FAIL":
+        if eval[0].label == "FAIL":
             fail_score = eval[0]["score"]
-        elif eval[0]["label"] == "SUCCESS":
+        elif eval[0].label == "SUCCESS":
             success_score = eval[0]["score"]
 
-        if eval[1]["label"] == "FAIL":
+        if eval[1].label == "FAIL":
             fail_score = eval[1]["score"]
-        elif eval[1]["label"] == "SUCCESS":
+        elif eval[1].label == "SUCCESS":
             success_score = eval[1]["score"]
 
         if fail_score < success_score: