diff --git a/README.md b/README.md
index 3e5d6cc..d5be0bf 100644
--- a/README.md
+++ b/README.md
@@ -302,7 +302,7 @@ logs = []
 for sample in dataset:
     prompt = template(sample)
     response = llm(prompt)
-    judge_output, score = judge(response)
+    judge_output, score = judge(response, sample.answer)
     
     logs.append({
 	    "sample": sample.model_dump(),
diff --git a/docs/quickstart/mcq.md b/docs/quickstart/mcq.md
index e20eb50..c692594 100644
--- a/docs/quickstart/mcq.md
+++ b/docs/quickstart/mcq.md
@@ -50,7 +50,7 @@ logs = []
 for sample in dataset:
     prompt = template(sample)
     response = llm(prompt)
-    judge_output, score = judge(response)
+    judge_output, score = judge(response, sample.answer)
     
     logs.append({
 	    "sample": sample.model_dump(),