diff --git a/tests/trace/test_evaluations.py b/tests/trace/test_evaluations.py
index f4993e9227d..019ea98cfd2 100644
--- a/tests/trace/test_evaluations.py
+++ b/tests/trace/test_evaluations.py
@@ -1021,11 +1021,11 @@ def my_second_scorer(text, output, model_output):
 
     ds = [{"text": "hello"}]
 
-    with pytest.raises(ValueError, match="Both 'output' and 'model_output'"):
+    with pytest.raises(ValueError, match="Both `output` and `model_output`"):
         scorer = MyScorer()
 
-    with pytest.raises(ValueError, match="Both 'output' and 'model_output'"):
+    with pytest.raises(ValueError, match="Both `output` and `model_output`"):
         evaluation = weave.Evaluation(dataset=ds, scorers=[MyScorer()])
 
-    with pytest.raises(ValueError, match="Both 'output' and 'model_output'"):
+    with pytest.raises(ValueError, match="Both `output` and `model_output`"):
         evaluation = weave.Evaluation(dataset=ds, scorers=[my_second_scorer])