diff --git a/langtest/metrics/llm_eval.py b/langtest/metrics/llm_eval.py
index ab510115b..99fc209ac 100644
--- a/langtest/metrics/llm_eval.py
+++ b/langtest/metrics/llm_eval.py
@@ -478,11 +478,13 @@ def evaluate_batch(self, examples: List[dict]) -> List[dict]:
         """
         results = []
         for example in examples:
-            prompt = example.get("prompt", "")
-            response = example.get("response", "")
-            groundtruth = example.get("groundtruth") if self.include_groundtruth else None
+            inputs = {
+                "prompt": example.get("prompt", ""),
+                "groundtruth": example.get("groundtruth"),
+            }
+            predictions = {"response": example.get("response", "")}
 
-            result = self.evaluate(prompt, response, groundtruth)
+            result = self.evaluate(inputs, predictions)
             results.append(result)
 
         return results
diff --git a/langtest/metrics/prometheus_eval.py b/langtest/metrics/prometheus_eval.py
index cc1b9d63c..2043bfd28 100644
--- a/langtest/metrics/prometheus_eval.py
+++ b/langtest/metrics/prometheus_eval.py
@@ -163,13 +163,7 @@ def evaluate_batch(self, entries: List[Dict[str, str]]) -> List[Tuple[str, int]]
         Returns:
             A list of tuples of feedback and score.
         """
-        queries = [entry.get("query", None) for entry in entries]
-        results = [entry.get("result", None) for entry in entries]
-        answers = [entry.get("answer", None) for entry in entries]
-        return [
-            self.evaluate_response(query, result, answer)
-            for query, result, answer in zip(queries, results, answers)
-        ]
+        return [self.evaluate_response(entry) for entry in entries]
 
     def evaluate(
         self,