diff --git a/tests/classify/test_evaluator.py b/tests/classify/test_evaluator.py
index 59253f80d8361878a365a290a31d7aaf7821b1a3..3ec5bbb7de2f4c92b8262e50cbc437c07c441758 100644
--- a/tests/classify/test_evaluator.py
+++ b/tests/classify/test_evaluator.py
@@ -40,10 +40,13 @@ def test_run_binary_1() -> None:
         ("s3", [1], [0.4]),
     ]
 
+    rng = numpy.random.default_rng(42)
+
     results = run(
         "test",
         predictions,
         binning=10,
+        rng=rng,
         threshold_a_priori=0.5,
     )
 
@@ -97,11 +100,14 @@ def test_run_binary_2() -> None:
         ("s3", [1], [0.4]),
     ]
 
+    rng = numpy.random.default_rng(42)
+
     # a change in the threshold should not affect auc and average precision scores
     results = run(
         "test",
         predictions,
         binning=10,
+        rng=rng,
         threshold_a_priori=0.3,
     )