diff --git a/tests/test_enviformer.py b/tests/test_enviformer.py
index ff14cdd8..b7994d4a 100644
--- a/tests/test_enviformer.py
+++ b/tests/test_enviformer.py
@@ -42,9 +42,7 @@ class EnviFormerTest(TestCase):
                 threshold = float(0.5)
                 data_package_objs = [self.BBD_SUBSET]
                 eval_packages_objs = [self.BBD_SUBSET]
-                mod = EnviFormer.create(
-                    self.package, data_package_objs, eval_packages_objs, threshold=threshold
-                )
+                mod = EnviFormer.create(self.package, data_package_objs, threshold=threshold)
 
                 mod.build_dataset()
                 mod.build_model()
@@ -57,12 +55,9 @@ class EnviFormerTest(TestCase):
             with self.settings(MODEL_DIR=tmpdir):
                 threshold = float(0.5)
                 data_package_objs = [self.BBD_SUBSET]
-                eval_packages_objs = [self.BBD_SUBSET]
                 mods = []
                 for _ in range(4):
-                    mod = EnviFormer.create(
-                        self.package, data_package_objs, eval_packages_objs, threshold=threshold
-                    )
+                    mod = EnviFormer.create(self.package, data_package_objs, threshold=threshold)
                     mod.build_dataset()
                     mod.build_model()
                     mods.append(mod)
diff --git a/tests/test_model.py b/tests/test_model.py
index bcee3992..50dfee19 100644
--- a/tests/test_model.py
+++ b/tests/test_model.py
@@ -72,7 +72,6 @@ class ModelTest(TestCase):
                     self.package,
                     rule_package_objs,
                     data_package_objs,
-                    eval_packages_objs,
                     threshold=threshold,
                     name="ECC - BBD - 0.5",
                     description="Created MLRelativeReasoning in Testcase",
@@ -84,9 +83,7 @@ class ModelTest(TestCase):
 
                 mod.build_dataset()
                 mod.build_model()
-                mod.multigen_eval = True
-                mod.save()
-                mod.evaluate_model(n_splits=2)
+                mod.evaluate_model(True, eval_packages_objs, n_splits=2)
 
                 results = mod.predict("CCN(CC)C(=O)C1=CC(=CC=C1)C")
 
@@ -103,7 +100,6 @@ class ModelTest(TestCase):
                     self.package,
                     rule_package_objs,
                     data_package_objs,
-                    eval_packages_objs,
                     threshold=threshold,
                     min_count=5,
                     max_count=0,
@@ -113,8 +109,6 @@ class ModelTest(TestCase):
 
                 mod.build_dataset()
                 mod.build_model()
-                mod.multigen_eval = True
-                mod.save()
-                mod.evaluate_model(n_splits=2)
+                mod.evaluate_model(True, eval_packages_objs, n_splits=2)
 
                 results = mod.predict("CCN(CC)C(=O)C1=CC(=CC=C1)C")