diff --git a/openml/extensions/sklearn/extension.py b/openml/extensions/sklearn/extension.py
index c3260e303..02322196e 100644
--- a/openml/extensions/sklearn/extension.py
+++ b/openml/extensions/sklearn/extension.py
@@ -13,7 +13,6 @@
 import traceback
 import warnings
 from collections import OrderedDict
-from distutils.version import LooseVersion
 from json.decoder import JSONDecodeError
 from re import IGNORECASE
 from typing import Any, Callable, List, Sized, cast
@@ -25,6 +24,7 @@
 import sklearn.base
 import sklearn.model_selection
 import sklearn.pipeline
+from packaging.version import Version
 
 import openml
 from openml.exceptions import PyOpenMLError
@@ -48,7 +48,7 @@
     r"(?P<version>(\d+\.)?(\d+\.)?(\d+)?(dev)?[0-9]*))?$",
 )
 
-sctypes = np.sctypes if LooseVersion(np.__version__) < "2.0" else np.core.sctypes
+sctypes = np.sctypes if Version(np.__version__) < Version("2.0") else np.core.sctypes
 SIMPLE_NUMPY_TYPES = [
     nptype
     for type_cat, nptypes in sctypes.items()
@@ -237,14 +237,13 @@ def _min_dependency_str(cls, sklearn_version: str) -> str:
         -------
         str
         """
-        openml_major_version = int(LooseVersion(openml.__version__).version[1])
         # This explicit check is necessary to support existing entities on the OpenML servers
         # that used the fixed dependency string (in the else block)
-        if openml_major_version > 11:
+        if Version(openml.__version__) > Version("0.11"):
             # OpenML v0.11 onwards supports sklearn>=0.24
             # assumption: 0.24 onwards sklearn should contain a _min_dependencies.py file with
             # variables declared for extracting minimum dependency for that version
-            if LooseVersion(sklearn_version) >= "0.24":
+            if Version(sklearn_version) >= Version("0.24"):
                 from sklearn import _min_dependencies as _mindep
 
                 dependency_list = {
@@ -253,18 +252,18 @@ def _min_dependency_str(cls, sklearn_version: str) -> str:
                     "joblib": f"{_mindep.JOBLIB_MIN_VERSION}",
                     "threadpoolctl": f"{_mindep.THREADPOOLCTL_MIN_VERSION}",
                 }
-            elif LooseVersion(sklearn_version) >= "0.23":
+            elif Version(sklearn_version) >= Version("0.23"):
                 dependency_list = {
                     "numpy": "1.13.3",
                     "scipy": "0.19.1",
                     "joblib": "0.11",
                     "threadpoolctl": "2.0.0",
                 }
-                if LooseVersion(sklearn_version).version[2] == 0:
+                if Version(sklearn_version).micro == 0:
                     dependency_list.pop("threadpoolctl")
-            elif LooseVersion(sklearn_version) >= "0.21":
+            elif Version(sklearn_version) >= Version("0.21"):
                 dependency_list = {"numpy": "1.11.0", "scipy": "0.17.0", "joblib": "0.11"}
-            elif LooseVersion(sklearn_version) >= "0.19":
+            elif Version(sklearn_version) >= Version("0.19"):
                 dependency_list = {"numpy": "1.8.2", "scipy": "0.13.3"}
             else:
                 dependency_list = {"numpy": "1.6.1", "scipy": "0.9"}
@@ -1226,8 +1225,8 @@ def _check_dependencies(
             version = match.group("version")
 
             module = importlib.import_module(dependency_name)
-            required_version = LooseVersion(version)
-            installed_version = LooseVersion(module.__version__)  # type: ignore
+            required_version = Version(version)
+            installed_version = Version(module.__version__)  # type: ignore
 
             if operation == "==":
                 check = required_version == installed_version
@@ -1258,7 +1257,7 @@ def _serialize_type(self, o: Any) -> OrderedDict[str, str]:
             np.int32: "np.int32",
             np.int64: "np.int64",
         }
-        if LooseVersion(np.__version__) < "1.24":
+        if Version(np.__version__) < Version("1.24"):
             mapping[float] = "np.float"
             mapping[int] = "np.int"
 
@@ -1278,7 +1277,7 @@ def _deserialize_type(self, o: str) -> Any:
         }
 
         # TODO(eddiebergman): Might be able to remove this
-        if LooseVersion(np.__version__) < "1.24":
+        if Version(np.__version__) < Version("1.24"):
             mapping["np.float"] = np.float  # type: ignore # noqa: NPY001
             mapping["np.int"] = np.int  # type: ignore # noqa: NPY001
 
diff --git a/pyproject.toml b/pyproject.toml
index 99ff2b804..b970a35b2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -19,6 +19,7 @@ dependencies = [
   "numpy>=1.6.2",
   "minio",
   "pyarrow",
+  "packaging",
 ]
 requires-python = ">=3.8"
 authors = [
diff --git a/tests/test_extensions/test_sklearn_extension/test_sklearn_extension.py b/tests/test_extensions/test_sklearn_extension/test_sklearn_extension.py
index cb4d0bc11..e181aaa15 100644
--- a/tests/test_extensions/test_sklearn_extension/test_sklearn_extension.py
+++ b/tests/test_extensions/test_sklearn_extension/test_sklearn_extension.py
@@ -9,7 +9,7 @@
 import unittest
 import warnings
 from collections import OrderedDict
-from distutils.version import LooseVersion
+from packaging.version import Version
 from typing import Any
 from unittest import mock
 
@@ -179,24 +179,24 @@ def _serialization_test_helper(
 
     @pytest.mark.sklearn()
     def test_serialize_model(self):
-        max_features = "auto" if LooseVersion(sklearn.__version__) < "1.3" else "sqrt"
+        max_features = "auto" if Version(sklearn.__version__) < Version("1.3") else "sqrt"
         model = sklearn.tree.DecisionTreeClassifier(
             criterion="entropy",
             max_features=max_features,
             max_leaf_nodes=2000,
         )
 
-        tree_name = "tree" if LooseVersion(sklearn.__version__) < "0.22" else "_classes"
+        tree_name = "tree" if Version(sklearn.__version__) < Version("0.22") else "_classes"
         fixture_name = f"sklearn.tree.{tree_name}.DecisionTreeClassifier"
         fixture_short_name = "sklearn.DecisionTreeClassifier"
         # str obtained from self.extension._get_sklearn_description(model)
         fixture_description = "A decision tree classifier."
         version_fixture = self.extension._min_dependency_str(sklearn.__version__)
 
-        presort_val = "false" if LooseVersion(sklearn.__version__) < "0.22" else '"deprecated"'
+        presort_val = "false" if Version(sklearn.__version__) < Version("0.22") else '"deprecated"'
         # min_impurity_decrease has been introduced in 0.20
         # min_impurity_split has been deprecated in 0.20
-        if LooseVersion(sklearn.__version__) < "0.19":
+        if Version(sklearn.__version__) < Version("0.19"):
             fixture_parameters = OrderedDict(
                 (
                     ("class_weight", "null"),
@@ -213,7 +213,7 @@ def test_serialize_model(self):
                     ("splitter", '"best"'),
                 ),
             )
-        elif LooseVersion(sklearn.__version__) < "1.0":
+        elif Version(sklearn.__version__) < Version("1.0"):
             fixture_parameters = OrderedDict(
                 (
                     ("class_weight", "null"),
@@ -231,7 +231,7 @@ def test_serialize_model(self):
                     ("splitter", '"best"'),
                 ),
             )
-        elif LooseVersion(sklearn.__version__) < "1.4":
+        elif Version(sklearn.__version__) < Version("1.4"):
             fixture_parameters = OrderedDict(
                 (
                     ("class_weight", "null"),
@@ -267,10 +267,10 @@ def test_serialize_model(self):
                 ),
             )
 
-        if LooseVersion(sklearn.__version__) >= "0.22":
+        if Version(sklearn.__version__) >= Version("0.22"):
             fixture_parameters.update({"ccp_alpha": "0.0"})
             fixture_parameters.move_to_end("ccp_alpha", last=False)
-        if LooseVersion(sklearn.__version__) >= "0.24":
+        if Version(sklearn.__version__) >= Version("0.24"):
             del fixture_parameters["presort"]
 
         structure_fixture = {f"sklearn.tree.{tree_name}.DecisionTreeClassifier": []}
@@ -307,30 +307,30 @@ def test_can_handle_flow(self):
     def test_serialize_model_clustering(self):
         model = sklearn.cluster.KMeans()
 
-        sklearn_version = LooseVersion(sklearn.__version__)
-        cluster_name = "k_means_" if sklearn_version < "0.22" else "_kmeans"
+        sklearn_version = Version(sklearn.__version__)
+        cluster_name = "k_means_" if sklearn_version < Version("0.22") else "_kmeans"
         fixture_name = f"sklearn.cluster.{cluster_name}.KMeans"
         fixture_short_name = "sklearn.KMeans"
         # str obtained from self.extension._get_sklearn_description(model)
         fixture_description = "K-Means clustering{}".format(
-            "" if sklearn_version < "0.22" else ".",
+            "" if sklearn_version < Version("0.22") else ".",
         )
         version_fixture = self.extension._min_dependency_str(sklearn.__version__)
 
         n_jobs_val = "1"
-        if sklearn_version >= "0.20":
+        if sklearn_version >= Version("0.20"):
             n_jobs_val = "null"
-        if sklearn_version >= "0.23":
+        if sklearn_version >= Version("0.23"):
             n_jobs_val = '"deprecated"'
 
-        precomp_val = '"auto"' if sklearn_version < "0.23" else '"deprecated"'
+        precomp_val = '"auto"' if sklearn_version < Version("0.23") else '"deprecated"'
         n_init = "10"
-        if sklearn_version >= "1.2":
+        if sklearn_version >= Version("1.2"):
             n_init = '"warn"'
-        if sklearn_version >= "1.4":
+        if sklearn_version >= Version("1.4"):
             n_init = '"auto"'
 
-        algorithm = '"auto"' if sklearn_version < "1.1" else '"lloyd"'
+        algorithm = '"auto"' if sklearn_version < Version("1.1") else '"lloyd"'
         fixture_parameters = OrderedDict([
             ("algorithm", algorithm),
             ("copy_x", "true"),
@@ -345,7 +345,7 @@ def test_serialize_model_clustering(self):
             ("verbose", "0"),
         ])
 
-        if sklearn_version >= "1.0":
+        if sklearn_version >= Version("1.0" ):
             fixture_parameters.pop("n_jobs")
             fixture_parameters.pop("precompute_distances")
 
@@ -369,7 +369,7 @@ def test_serialize_model_clustering(self):
 
     @pytest.mark.sklearn()
     def test_serialize_model_with_subcomponent(self):
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         estimator_param = {estimator_name: sklearn.tree.DecisionTreeClassifier()}
         model = sklearn.ensemble.AdaBoostClassifier(
             n_estimators=100,
@@ -377,9 +377,9 @@ def test_serialize_model_with_subcomponent(self):
         )
 
         weight_name = "{}weight_boosting".format(
-            "" if LooseVersion(sklearn.__version__) < "0.22" else "_",
+            "" if Version(sklearn.__version__) < Version("0.22") else "_",
         )
-        tree_name = "tree" if LooseVersion(sklearn.__version__) < "0.22" else "_classes"
+        tree_name = "tree" if Version(sklearn.__version__) < Version("0.22") else "_classes"
         fixture_name = (
             f"sklearn.ensemble.{weight_name}.AdaBoostClassifier"
             f"({estimator_name}=sklearn.tree.{tree_name}.DecisionTreeClassifier)"
@@ -417,7 +417,7 @@ def test_serialize_model_with_subcomponent(self):
         assert serialization.name == fixture_name
         assert serialization.class_name == fixture_class_name
         assert serialization.custom_name == fixture_short_name
-        if LooseVersion(sklearn.__version__) < "1.4":
+        if Version(sklearn.__version__) < Version("1.4"):
             assert serialization.description == fixture_description
         assert serialization.parameters["algorithm"] == '"SAMME.R"'
         assert isinstance(serialization.parameters[estimator_name], str)
@@ -439,7 +439,7 @@ def test_serialize_pipeline(self):
         dummy = sklearn.dummy.DummyClassifier(strategy="prior")
         model = sklearn.pipeline.Pipeline(steps=[("scaler", scaler), ("dummy", dummy)])
 
-        scaler_name = "data" if LooseVersion(sklearn.__version__) < "0.22" else "_data"
+        scaler_name = "data" if Version(sklearn.__version__) < Version("0.22") else "_data"
         fixture_name = (
             "sklearn.pipeline.Pipeline("
             f"scaler=sklearn.preprocessing.{scaler_name}.StandardScaler,"
@@ -464,7 +464,7 @@ def test_serialize_pipeline(self):
 
         assert serialization.name == fixture_name
         assert serialization.custom_name == fixture_short_name
-        if LooseVersion(sklearn.__version__) < "1.3":
+        if Version(sklearn.__version__) < Version("1.3"):
             # Newer versions of scikit-learn have update docstrings
             assert serialization.description == fixture_description
         self.assertDictEqual(structure, fixture_structure)
@@ -473,9 +473,9 @@ def test_serialize_pipeline(self):
         # The parameters only have the name of base objects(not the whole flow)
         # as value
         # memory parameter has been added in 0.19, verbose in 0.21
-        if LooseVersion(sklearn.__version__) < "0.19":
+        if Version(sklearn.__version__) < Version("0.19"):
             assert len(serialization.parameters) == 1
-        elif LooseVersion(sklearn.__version__) < "0.21":
+        elif Version(sklearn.__version__) < Version("0.21"):
             assert len(serialization.parameters) == 2
         else:
             assert len(serialization.parameters) == 3
@@ -508,8 +508,8 @@ def test_serialize_pipeline_clustering(self):
         km = sklearn.cluster.KMeans()
         model = sklearn.pipeline.Pipeline(steps=[("scaler", scaler), ("clusterer", km)])
 
-        scaler_name = "data" if LooseVersion(sklearn.__version__) < "0.22" else "_data"
-        cluster_name = "k_means_" if LooseVersion(sklearn.__version__) < "0.22" else "_kmeans"
+        scaler_name = "data" if Version(sklearn.__version__) < Version("0.22") else "_data"
+        cluster_name = "k_means_" if Version(sklearn.__version__) < Version("0.22") else "_kmeans"
         fixture_name = (
             "sklearn.pipeline.Pipeline("
             f"scaler=sklearn.preprocessing.{scaler_name}.StandardScaler,"
@@ -533,7 +533,7 @@ def test_serialize_pipeline_clustering(self):
 
         assert serialization.name == fixture_name
         assert serialization.custom_name == fixture_short_name
-        if LooseVersion(sklearn.__version__) < "1.3":
+        if Version(sklearn.__version__) < Version("1.3"):
             # Newer versions of scikit-learn have update docstrings
             assert serialization.description == fixture_description
         self.assertDictEqual(structure, fixture_structure)
@@ -542,9 +542,9 @@ def test_serialize_pipeline_clustering(self):
         # The parameters only have the name of base objects(not the whole flow)
         # as value
         # memory parameter has been added in 0.19
-        if LooseVersion(sklearn.__version__) < "0.19":
+        if Version(sklearn.__version__) < Version("0.19"):
             assert len(serialization.parameters) == 1
-        elif LooseVersion(sklearn.__version__) < "0.21":
+        elif Version(sklearn.__version__) < Version("0.21"):
             assert len(serialization.parameters) == 2
         else:
             assert len(serialization.parameters) == 3
@@ -572,7 +572,7 @@ def test_serialize_pipeline_clustering(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     def test_serialize_column_transformer(self):
@@ -592,7 +592,7 @@ def test_serialize_column_transformer(self):
             remainder="passthrough",
         )
 
-        scaler_name = "data" if LooseVersion(sklearn.__version__) < "0.22" else "_data"
+        scaler_name = "data" if Version(sklearn.__version__) < Version("0.22") else "_data"
         fixture = (
             "sklearn.compose._column_transformer.ColumnTransformer("
             f"numeric=sklearn.preprocessing.{scaler_name}.StandardScaler,"
@@ -631,7 +631,7 @@ def test_serialize_column_transformer(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     def test_serialize_column_transformer_pipeline(self):
@@ -652,8 +652,8 @@ def test_serialize_column_transformer_pipeline(self):
         model = sklearn.pipeline.Pipeline(
             steps=[("transformer", inner), ("classifier", sklearn.tree.DecisionTreeClassifier())],
         )
-        scaler_name = "data" if LooseVersion(sklearn.__version__) < "0.22" else "_data"
-        tree_name = "tree" if LooseVersion(sklearn.__version__) < "0.22" else "_classes"
+        scaler_name = "data" if Version(sklearn.__version__) < Version("0.22") else "_data"
+        tree_name = "tree" if Version(sklearn.__version__) < Version("0.22") else "_classes"
         fixture_name = (
             "sklearn.pipeline.Pipeline("
             "transformer=sklearn.compose._column_transformer."
@@ -692,19 +692,19 @@ def test_serialize_column_transformer_pipeline(self):
         )
         structure = serialization.get_structure("name")
         assert serialization.name == fixture_name
-        if LooseVersion(sklearn.__version__) < "1.3":  # Not yet up-to-date for later versions
+        if Version(sklearn.__version__) < Version("1.3"):  # Not yet up-to-date for later versions
             assert serialization.description == fixture_description
         self.assertDictEqual(structure, fixture_structure)
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="Pipeline processing behaviour updated",
     )
     def test_serialize_feature_union(self):
-        sparse_parameter = "sparse" if LooseVersion(sklearn.__version__) < "1.4" else "sparse_output" 
+        sparse_parameter = "sparse" if Version(sklearn.__version__) < Version("1.4") else "sparse_output"
         ohe_params = {sparse_parameter: False}
-        if LooseVersion(sklearn.__version__) >= "0.20":
+        if Version(sklearn.__version__) >= Version("0.20"):
             ohe_params["categories"] = "auto"
         ohe = sklearn.preprocessing.OneHotEncoder(**ohe_params)
         scaler = sklearn.preprocessing.StandardScaler()
@@ -719,8 +719,8 @@ def test_serialize_feature_union(self):
         )
         structure = serialization.get_structure("name")
         # OneHotEncoder was moved to _encoders module in 0.20
-        module_name_encoder = "_encoders" if LooseVersion(sklearn.__version__) >= "0.20" else "data"
-        scaler_name = "data" if LooseVersion(sklearn.__version__) < "0.22" else "_data"
+        module_name_encoder = "_encoders" if Version(sklearn.__version__) >= Version("0.20") else "data"
+        scaler_name = "data" if Version(sklearn.__version__) < Version("0.22") else "_data"
         fixture_name = (
             "sklearn.pipeline.FeatureUnion("
             f"ohe=sklearn.preprocessing.{module_name_encoder}.OneHotEncoder,"
@@ -765,7 +765,7 @@ def test_serialize_feature_union(self):
 
     @pytest.mark.sklearn()
     def test_serialize_feature_union_switched_names(self):
-        ohe_params = {"categories": "auto"} if LooseVersion(sklearn.__version__) >= "0.20" else {}
+        ohe_params = {"categories": "auto"} if Version(sklearn.__version__) >= Version("0.20") else {}
         ohe = sklearn.preprocessing.OneHotEncoder(**ohe_params)
         scaler = sklearn.preprocessing.StandardScaler()
         fu1 = sklearn.pipeline.FeatureUnion(transformer_list=[("ohe", ohe), ("scaler", scaler)])
@@ -787,8 +787,8 @@ def test_serialize_feature_union_switched_names(self):
         )
 
         # OneHotEncoder was moved to _encoders module in 0.20
-        module_name_encoder = "_encoders" if LooseVersion(sklearn.__version__) >= "0.20" else "data"
-        scaler_name = "data" if LooseVersion(sklearn.__version__) < "0.22" else "_data"
+        module_name_encoder = "_encoders" if Version(sklearn.__version__) >= Version("0.20") else "data"
+        scaler_name = "data" if Version(sklearn.__version__) < Version("0.22") else "_data"
         assert (
             fu1_serialization.name == "sklearn.pipeline.FeatureUnion("
             f"ohe=sklearn.preprocessing.{module_name_encoder}.OneHotEncoder,"
@@ -802,7 +802,7 @@ def test_serialize_feature_union_switched_names(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) >= "1.4",
+        Version(sklearn.__version__) >= Version("1.4"),
         "AdaBoost parameter name changed as did the way its forwarded to GridSearchCV",
     )
     def test_serialize_complex_flow(self):
@@ -836,15 +836,15 @@ def test_serialize_complex_flow(self):
         )
         structure = serialized.get_structure("name")
         # OneHotEncoder was moved to _encoders module in 0.20
-        module_name_encoder = "_encoders" if LooseVersion(sklearn.__version__) >= "0.20" else "data"
+        module_name_encoder = "_encoders" if Version(sklearn.__version__) >= Version("0.20") else "data"
         ohe_name = "sklearn.preprocessing.%s.OneHotEncoder" % module_name_encoder
         scaler_name = "sklearn.preprocessing.{}.StandardScaler".format(
-            "data" if LooseVersion(sklearn.__version__) < "0.22" else "_data",
+            "data" if Version(sklearn.__version__) < Version("0.22") else "_data",
         )
         tree_name = "sklearn.tree.{}.DecisionTreeClassifier".format(
-            "tree" if LooseVersion(sklearn.__version__) < "0.22" else "_classes",
+            "tree" if Version(sklearn.__version__) < Version("0.22") else "_classes",
         )
-        weight_name = "weight" if LooseVersion(sklearn.__version__) < "0.22" else "_weight"
+        weight_name = "weight" if Version(sklearn.__version__) < Version("0.22") else "_weight"
         boosting_name = "sklearn.ensemble.{}_boosting.AdaBoostClassifier(base_estimator={})".format(
             weight_name,
             tree_name,
@@ -870,7 +870,7 @@ def test_serialize_complex_flow(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.21",
+        Version(sklearn.__version__) < Version("0.21"),
         reason="Pipeline till 0.20 doesn't support 'passthrough'",
     )
     def test_serialize_strings_as_pipeline_steps(self):
@@ -971,7 +971,7 @@ def test_serialize_strings_as_pipeline_steps(self):
     @pytest.mark.sklearn()
     def test_serialize_type(self):
         supported_types = [float, np.float32, np.float64, int, np.int32, np.int64]
-        if LooseVersion(np.__version__) < "1.24":
+        if Version(np.__version__) < Version("1.24"):
             supported_types.append(float)
             supported_types.append(int)
 
@@ -1294,7 +1294,7 @@ def test_paralizable_check(self):
         # using this param distribution should not raise an exception
         legal_param_dist = {"n_estimators": [2, 3, 4]}
 
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         legal_models = [
             sklearn.ensemble.RandomForestClassifier(),
             sklearn.ensemble.RandomForestClassifier(n_jobs=5),
@@ -1320,7 +1320,7 @@ def test_paralizable_check(self):
             sklearn.model_selection.GridSearchCV(multicore_bagging, illegal_param_dist),
         ]
 
-        if LooseVersion(sklearn.__version__) < "0.20":
+        if Version(sklearn.__version__) < Version("0.20"):
             has_refit_time = [False, False, False, False, False, False, False, False, False]
         else:
             has_refit_time = [False, False, False, False, False, False, True, True, False]
@@ -1336,44 +1336,44 @@ def test_paralizable_check(self):
 
     @pytest.mark.sklearn()
     def test__get_fn_arguments_with_defaults(self):
-        sklearn_version = LooseVersion(sklearn.__version__)
-        if sklearn_version < "0.19":
+        sklearn_version = Version(sklearn.__version__)
+        if sklearn_version < Version("0.19"):
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 15),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 12),
                 (sklearn.pipeline.Pipeline.__init__, 0),
             ]
-        elif sklearn_version < "0.21":
+        elif sklearn_version < Version("0.21"):
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 16),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 13),
                 (sklearn.pipeline.Pipeline.__init__, 1),
             ]
-        elif sklearn_version < "0.22":
+        elif sklearn_version < Version("0.22"):
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 16),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 13),
                 (sklearn.pipeline.Pipeline.__init__, 2),
             ]
-        elif sklearn_version < "0.23":
+        elif sklearn_version < Version("0.23"):
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 18),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 14),
                 (sklearn.pipeline.Pipeline.__init__, 2),
             ]
-        elif sklearn_version < "0.24":
+        elif sklearn_version < Version("0.24"):
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 18),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 14),
                 (sklearn.pipeline.Pipeline.__init__, 2),
             ]
-        elif sklearn_version < "1.0":
+        elif sklearn_version < Version("1.0"):
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 18),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 13),
                 (sklearn.pipeline.Pipeline.__init__, 2),
             ]
-        elif sklearn_version < "1.4":
+        elif sklearn_version < Version("1.4"):
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 17),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 12),
@@ -1410,13 +1410,13 @@ def test_deserialize_with_defaults(self):
         pipe_orig = sklearn.pipeline.Pipeline(steps=steps)
 
         pipe_adjusted = sklearn.clone(pipe_orig)
-        if LooseVersion(sklearn.__version__) < "0.23":
+        if Version(sklearn.__version__) < Version("0.23"):
             params = {
                 "Imputer__strategy": "median",
                 "OneHotEncoder__sparse": False,
                 "Estimator__min_samples_leaf": 42,
             }
-        elif LooseVersion(sklearn.__version__) < "1.4":
+        elif Version(sklearn.__version__) < Version("1.4"):
             params = {
                 "Imputer__strategy": "mean",
                 "OneHotEncoder__sparse": True,
@@ -1455,13 +1455,13 @@ def test_deserialize_adaboost_with_defaults(self):
         pipe_orig = sklearn.pipeline.Pipeline(steps=steps)
 
         pipe_adjusted = sklearn.clone(pipe_orig)
-        if LooseVersion(sklearn.__version__) < "0.22":
+        if Version(sklearn.__version__) < Version("0.22"):
             params = {
                 "Imputer__strategy": "median",
                 "OneHotEncoder__sparse": False,
                 "Estimator__n_estimators": 10,
             }
-        elif LooseVersion(sklearn.__version__) < "1.4":
+        elif Version(sklearn.__version__) < Version("1.4"):
             params = {
                 "Imputer__strategy": "mean",
                 "OneHotEncoder__sparse": True,
@@ -1504,11 +1504,11 @@ def test_deserialize_complex_with_defaults(self):
         pipe_orig = sklearn.pipeline.Pipeline(steps=steps)
 
         pipe_adjusted = sklearn.clone(pipe_orig)
-        impute_strategy = "median" if LooseVersion(sklearn.__version__) < "0.23" else "mean"
-        sparse = LooseVersion(sklearn.__version__) >= "0.23"
-        sparse_parameter = "sparse" if LooseVersion(sklearn.__version__) < "1.4" else "sparse_output"
+        impute_strategy = "median" if Version(sklearn.__version__) < Version("0.23") else "mean"
+        sparse = Version(sklearn.__version__) >= Version("0.23")
+        sparse_parameter = "sparse" if Version(sklearn.__version__) < Version("1.4") else "sparse_output"
         estimator_name = (
-            "base_estimator" if LooseVersion(sklearn.__version__) < "1.2" else "estimator"
+            "base_estimator" if Version(sklearn.__version__) < Version("1.2") else "estimator"
         )
         params = {
             "Imputer__strategy": impute_strategy,
@@ -1532,7 +1532,7 @@ def test_deserialize_complex_with_defaults(self):
     @pytest.mark.sklearn()
     def test_openml_param_name_to_sklearn(self):
         scaler = sklearn.preprocessing.StandardScaler(with_mean=False)
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         boosting = sklearn.ensemble.AdaBoostClassifier(
             **{estimator_name: sklearn.tree.DecisionTreeClassifier()},
         )
@@ -1569,13 +1569,13 @@ def test_openml_param_name_to_sklearn(self):
     def test_obtain_parameter_values_flow_not_from_server(self):
         model = sklearn.linear_model.LogisticRegression(solver="lbfgs")
         flow = self.extension.model_to_flow(model)
-        logistic_name = "logistic" if LooseVersion(sklearn.__version__) < "0.22" else "_logistic"
+        logistic_name = "logistic" if Version(sklearn.__version__) < Version("0.22") else "_logistic"
         msg = f"Flow sklearn.linear_model.{logistic_name}.LogisticRegression has no flow_id!"
 
         with pytest.raises(ValueError, match=msg):
             self.extension.obtain_parameter_values(flow)
 
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         model = sklearn.ensemble.AdaBoostClassifier(
             **{
                 estimator_name: sklearn.linear_model.LogisticRegression(
@@ -1768,7 +1768,7 @@ def test_run_model_on_fold_classification_1_array(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.21",
+        Version(sklearn.__version__) < Version("0.21"),
         reason="SimpleImputer, ColumnTransformer available only after 0.19 and "
         "Pipeline till 0.20 doesn't support indexing and 'passthrough'",
     )
@@ -1786,7 +1786,7 @@ def test_run_model_on_fold_classification_1_dataframe(self):
         y_test = y.iloc[test_indices]
 
         # Helper functions to return required columns for ColumnTransformer
-        sparse = {"sparse" if LooseVersion(sklearn.__version__) < "1.4" else "sparse_output": False}
+        sparse = {"sparse" if Version(sklearn.__version__) < Version("1.4") else "sparse_output": False}
         cat_imp = make_pipeline(
             SimpleImputer(strategy="most_frequent"),
             OneHotEncoder(handle_unknown="ignore", **sparse),
@@ -2173,7 +2173,7 @@ def test_trim_flow_name(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.21",
+        Version(sklearn.__version__) < Version("0.21"),
         reason="SimpleImputer, ColumnTransformer available only after 0.19 and "
         "Pipeline till 0.20 doesn't support indexing and 'passthrough'",
     )
@@ -2230,7 +2230,7 @@ def test_run_on_model_with_empty_steps(self):
         assert isinstance(flow.components["dummystep"], OpenMLFlow)
         assert flow.components["dummystep"].name == "passthrough"
         assert isinstance(flow.components["classifier"], OpenMLFlow)
-        if LooseVersion(sklearn.__version__) < "0.22":
+        if Version(sklearn.__version__) < Version("0.22"):
             assert flow.components["classifier"].name == "sklearn.svm.classes.SVC"
         else:
             assert flow.components["classifier"].name == "sklearn.svm._classes.SVC"
@@ -2276,7 +2276,7 @@ def test_sklearn_serialization_with_none_step(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     def test_failed_serialization_of_custom_class(self):
@@ -2313,7 +2313,7 @@ def test_failed_serialization_of_custom_class(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     def test_setupid_with_column_transformer(self):
diff --git a/tests/test_flows/test_flow.py b/tests/test_flows/test_flow.py
index 2e81c7ae3..dafbeaf3c 100644
--- a/tests/test_flows/test_flow.py
+++ b/tests/test_flows/test_flow.py
@@ -6,7 +6,7 @@
 import hashlib
 import re
 import time
-from distutils.version import LooseVersion
+from packaging.version import Version
 from unittest import mock
 
 import pytest
@@ -156,7 +156,7 @@ def test_from_xml_to_xml(self):
     @pytest.mark.sklearn()
     def test_to_xml_from_xml(self):
         scaler = sklearn.preprocessing.StandardScaler(with_mean=False)
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         boosting = sklearn.ensemble.AdaBoostClassifier(
             **{estimator_name: sklearn.tree.DecisionTreeClassifier()},
         )
@@ -269,7 +269,7 @@ def test_semi_legal_flow(self):
         # TODO: Test if parameters are set correctly!
         # should not throw error as it contains two differentiable forms of
         # Bagging i.e., Bagging(Bagging(J48)) and Bagging(J48)
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         semi_legal = sklearn.ensemble.BaggingClassifier(
             **{
                 estimator_name: sklearn.ensemble.BaggingClassifier(
@@ -311,7 +311,7 @@ def test_publish_error(self, api_call_mock, flow_exists_mock, get_flow_mock):
         get_flow_mock.return_value = flow_copy
         flow_exists_mock.return_value = 1
 
-        if LooseVersion(sklearn.__version__) < "0.22":
+        if Version(sklearn.__version__) < Version("0.22"):
             fixture = (
                 "The flow on the server is inconsistent with the local flow. "
                 "The server flow ID is 1. Please check manually and remove "
@@ -375,9 +375,9 @@ def test_existing_flow_exists(self):
         # create a flow
         nb = sklearn.naive_bayes.GaussianNB()
 
-        sparse = "sparse" if LooseVersion(sklearn.__version__) < "1.4" else "sparse_output"
+        sparse = "sparse" if Version(sklearn.__version__) < Version("1.4") else "sparse_output"
         ohe_params = {sparse: False, "handle_unknown": "ignore"}
-        if LooseVersion(sklearn.__version__) >= "0.20":
+        if Version(sklearn.__version__) >= Version("0.20"):
             ohe_params["categories"] = "auto"
         steps = [
             ("imputation", SimpleImputer(strategy="median")),
@@ -418,7 +418,7 @@ def test_sklearn_to_upload_to_flow(self):
 
         # Test a more complicated flow
         ohe_params = {"handle_unknown": "ignore"}
-        if LooseVersion(sklearn.__version__) >= "0.20":
+        if Version(sklearn.__version__) >= Version("0.20"):
             ohe_params["categories"] = "auto"
         ohe = sklearn.preprocessing.OneHotEncoder(**ohe_params)
         scaler = sklearn.preprocessing.StandardScaler(with_mean=False)
@@ -428,7 +428,7 @@ def test_sklearn_to_upload_to_flow(self):
             percentile=30,
         )
         fu = sklearn.pipeline.FeatureUnion(transformer_list=[("pca", pca), ("fs", fs)])
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         boosting = sklearn.ensemble.AdaBoostClassifier(
             **{estimator_name: sklearn.tree.DecisionTreeClassifier()},
         )
@@ -499,8 +499,8 @@ def test_sklearn_to_upload_to_flow(self):
         assert new_flow is not flow
 
         # OneHotEncoder was moved to _encoders module in 0.20
-        module_name_encoder = "_encoders" if LooseVersion(sklearn.__version__) >= "0.20" else "data"
-        if LooseVersion(sklearn.__version__) < "0.22":
+        module_name_encoder = "_encoders" if Version(sklearn.__version__) >= Version("0.20") else "data"
+        if Version(sklearn.__version__) < Version("0.22"):
             fixture_name = (
                 f"{sentinel}sklearn.model_selection._search.RandomizedSearchCV("
                 "estimator=sklearn.pipeline.Pipeline("
diff --git a/tests/test_flows/test_flow_functions.py b/tests/test_flows/test_flow_functions.py
index 6fd2bb765..f9ce97c2f 100644
--- a/tests/test_flows/test_flow_functions.py
+++ b/tests/test_flows/test_flow_functions.py
@@ -5,7 +5,7 @@
 import functools
 import unittest
 from collections import OrderedDict
-from distutils.version import LooseVersion
+from packaging.version import Version
 from unittest import mock
 from unittest.mock import patch
 
@@ -279,7 +279,7 @@ def test_are_flows_equal_ignore_if_older(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="OrdinalEncoder introduced in 0.20. "
         "No known models with list of lists parameters in older versions.",
     )
@@ -334,7 +334,7 @@ def test_get_flow_reinstantiate_model_no_extension(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) == "0.19.1",
+        Version(sklearn.__version__) == Version("0.19.1"),
         reason="Requires scikit-learn!=0.19.1, because target flow is from that version.",
     )
     @pytest.mark.production()
@@ -353,7 +353,7 @@ def test_get_flow_with_reinstantiate_strict_with_wrong_version_raises_exception(
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) >= "1.0.0",
+        Version(sklearn.__version__) >= Version("1.0.0"),
         reason="Requires scikit-learn < 1.0.0.",
         # Because scikit-learn dropped min_impurity_split hyperparameter in 1.0,
         # and the requested flow is from 1.0.0 exactly.
@@ -367,8 +367,8 @@ def test_get_flow_reinstantiate_flow_not_strict_post_1(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        (LooseVersion(sklearn.__version__) < "0.23.2")
-        or (LooseVersion(sklearn.__version__) >= "1.0"),
+        (Version(sklearn.__version__) < Version("0.23.2"))
+        or (Version(sklearn.__version__) >= Version("1.0")),
         reason="Requires scikit-learn 0.23.2 or ~0.24.",
         # Because these still have min_impurity_split, but with new scikit-learn module structure."
     )
@@ -381,7 +381,7 @@ def test_get_flow_reinstantiate_flow_not_strict_023_and_024(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) > "0.23",
+        Version(sklearn.__version__) > Version("0.23"),
         reason="Requires scikit-learn<=0.23, because the scikit-learn module structure changed.",
     )
     @pytest.mark.production()
diff --git a/tests/test_runs/test_run_functions.py b/tests/test_runs/test_run_functions.py
index 2106173da..40a778d8b 100644
--- a/tests/test_runs/test_run_functions.py
+++ b/tests/test_runs/test_run_functions.py
@@ -7,7 +7,7 @@
 import time
 import unittest
 import warnings
-from distutils.version import LooseVersion
+from packaging.version import Version
 from unittest import mock
 
 import arff
@@ -249,7 +249,7 @@ def _perform_run(
             "sklearn.model_selection._search.GridSearchCV",
             "sklearn.pipeline.Pipeline",
         ]
-        if LooseVersion(sklearn.__version__) < "0.22":
+        if Version(sklearn.__version__) < Version("0.22"):
             classes_without_random_state.append("sklearn.linear_model.base.LinearRegression")
         else:
             classes_without_random_state.append("sklearn.linear_model._base.LinearRegression")
@@ -680,7 +680,7 @@ def test_run_and_upload_pipeline_dummy_pipeline(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     def test_run_and_upload_column_transformer_pipeline(self):
@@ -745,7 +745,7 @@ def get_ct_cf(nominal_indices, numeric_indices):
     @pytest.mark.sklearn()
     @unittest.skip("https://github.com/openml/OpenML/issues/1180")
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     @mock.patch("warnings.warn")
@@ -796,7 +796,7 @@ def test_run_and_upload_knn_pipeline(self, warnings_mock):
 
     @pytest.mark.sklearn()
     def test_run_and_upload_gridsearch(self):
-        estimator_name = "base_estimator" if LooseVersion(sklearn.__version__) < "1.4" else "estimator"
+        estimator_name = "base_estimator" if Version(sklearn.__version__) < Version("1.4") else "estimator"
         gridsearch = GridSearchCV(
             BaggingClassifier(**{estimator_name: SVC()}),
             {f"{estimator_name}__C": [0.01, 0.1, 10], f"{estimator_name}__gamma": [0.01, 0.1, 10]},
@@ -935,7 +935,7 @@ def test_learning_curve_task_2(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.21",
+        Version(sklearn.__version__) < Version("0.21"),
         reason="Pipelines don't support indexing (used for the assert check)",
     )
     def test_initialize_cv_from_run(self):
@@ -998,7 +998,7 @@ def _test_local_evaluations(self, run):
             (sklearn.metrics.precision_score, {"average": "macro"}),
             (sklearn.metrics.brier_score_loss, {}),
         ]
-        if LooseVersion(sklearn.__version__) < "0.23":
+        if Version(sklearn.__version__) < Version("0.23"):
             tests.append((sklearn.metrics.jaccard_similarity_score, {}))
         else:
             tests.append((sklearn.metrics.jaccard_score, {}))
@@ -1030,7 +1030,7 @@ def test_local_run_swapped_parameter_order_model(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="SimpleImputer doesn't handle mixed type DataFrame as input",
     )
     def test_local_run_swapped_parameter_order_flow(self):
@@ -1059,7 +1059,7 @@ def test_local_run_swapped_parameter_order_flow(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="SimpleImputer doesn't handle mixed type DataFrame as input",
     )
     def test_local_run_metric_score(self):
@@ -1097,7 +1097,7 @@ def test_online_run_metric_score(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="SimpleImputer doesn't handle mixed type DataFrame as input",
     )
     def test_initialize_model_from_run(self):
@@ -1159,7 +1159,7 @@ def test_initialize_model_from_run(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="SimpleImputer doesn't handle mixed type DataFrame as input",
     )
     def test__run_exists(self):
@@ -1333,7 +1333,7 @@ def test_run_with_illegal_flow_id_1_after_load(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="OneHotEncoder cannot handle mixed type DataFrame as input",
     )
     def test__run_task_get_arffcontent(self):
@@ -1341,7 +1341,7 @@ def test__run_task_get_arffcontent(self):
         num_instances = 3196
         num_folds = 10
         num_repeats = 1
-        loss = "log" if LooseVersion(sklearn.__version__) < "1.3" else "log_loss"
+        loss = "log" if Version(sklearn.__version__) < Version("1.3") else "log_loss"
 
         clf = make_pipeline(
             OneHotEncoder(handle_unknown="ignore"),
@@ -1572,7 +1572,7 @@ def test_get_runs_list_by_tag(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     def test_run_on_dataset_with_missing_labels_dataframe(self):
@@ -1609,7 +1609,7 @@ def test_run_on_dataset_with_missing_labels_dataframe(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="columntransformer introduction in 0.20.0",
     )
     def test_run_on_dataset_with_missing_labels_array(self):
@@ -1757,7 +1757,7 @@ def test_format_prediction_task_regression(self):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.21",
+        Version(sklearn.__version__) < Version("0.21"),
         reason="couldn't perform local tests successfully w/o bloating RAM",
     )
     @mock.patch("openml.extensions.sklearn.SklearnExtension._prevent_optimize_n_jobs")
@@ -1767,10 +1767,10 @@ def test__run_task_get_arffcontent_2(self, parallel_mock):
         x, y = task.get_X_and_y(dataset_format="dataframe")
         num_instances = x.shape[0]
         line_length = 6 + len(task.class_labels)
-        loss = "log" if LooseVersion(sklearn.__version__) < "1.3" else "log_loss"
+        loss = "log" if Version(sklearn.__version__) < Version("1.3") else "log_loss"
         clf = SGDClassifier(loss=loss, random_state=1)
         n_jobs = 2
-        backend = "loky" if LooseVersion(joblib.__version__) > "0.11" else "multiprocessing"
+        backend = "loky" if Version(joblib.__version__) > Version("0.11") else "multiprocessing"
         with parallel_backend(backend, n_jobs=n_jobs):
             res = openml.runs.functions._run_task_get_arffcontent(
                 extension=self.extension,
@@ -1815,7 +1815,7 @@ def test__run_task_get_arffcontent_2(self, parallel_mock):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.21",
+        Version(sklearn.__version__) < Version("0.21"),
         reason="couldn't perform local tests successfully w/o bloating RAM",
     )
     @mock.patch("openml.extensions.sklearn.SklearnExtension._prevent_optimize_n_jobs")
@@ -1826,7 +1826,7 @@ def test_joblib_backends(self, parallel_mock):
         num_instances = x.shape[0]
         line_length = 6 + len(task.class_labels)
 
-        backend_choice = "loky" if LooseVersion(joblib.__version__) > "0.11" else "multiprocessing"
+        backend_choice = "loky" if Version(joblib.__version__) > Version("0.11") else "multiprocessing"
         for n_jobs, backend, call_count in [
             (1, backend_choice, 10),
             (2, backend_choice, 10),
@@ -1873,7 +1873,7 @@ def test_joblib_backends(self, parallel_mock):
             assert parallel_mock.call_count == call_count
 
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.20",
+        Version(sklearn.__version__) < Version("0.20"),
         reason="SimpleImputer doesn't handle mixed type DataFrame as input",
     )
     def test_delete_run(self):
diff --git a/tests/test_study/test_study_examples.py b/tests/test_study/test_study_examples.py
index b3f418756..9e5cb4e5e 100644
--- a/tests/test_study/test_study_examples.py
+++ b/tests/test_study/test_study_examples.py
@@ -2,7 +2,7 @@
 from __future__ import annotations
 
 import unittest
-from distutils.version import LooseVersion
+from packaging.version import Version
 
 import pytest
 import sklearn
@@ -17,7 +17,7 @@ class TestStudyFunctions(TestBase):
 
     @pytest.mark.sklearn()
     @unittest.skipIf(
-        LooseVersion(sklearn.__version__) < "0.24",
+        Version(sklearn.__version__) < Version("0.24"),
         reason="columntransformer introduction in 0.24.0",
     )
     def test_Figure1a(self):