diff --git a/src/safeds/ml/classification/_classifier.py b/src/safeds/ml/classification/_classifier.py
index a0423ab09..7e9e9e731 100644
--- a/src/safeds/ml/classification/_classifier.py
+++ b/src/safeds/ml/classification/_classifier.py
@@ -1,6 +1,7 @@
 from abc import ABC, abstractmethod
 
 from safeds.data.tabular.containers import Table, TaggedTable
+from sklearn.metrics import accuracy_score as sk_accuracy_score
 
 
 class Classifier(ABC):
@@ -44,3 +45,25 @@ def predict(self, dataset: Table) -> TaggedTable:
         PredictionError
             If prediction with the given dataset failed.
         """
+
+    def accuracy(self, validation_or_test_set: TaggedTable) -> float:
+        """
+        Predicts the target values for the features in the validation or test set and compares it to the expected
+        results.
+
+        Parameters
+        ----------
+        validation_or_test_set : TaggedTable
+            The validation or test set.
+
+        Returns
+        -------
+        accuracy : float
+            The calculated accuracy score, i.e. the percentage of equal data.
+        """
+
+        expected = validation_or_test_set.target
+        predicted = self.predict(validation_or_test_set.features).target
+
+        # noinspection PyProtectedMember
+        return sk_accuracy_score(expected._data, predicted._data)
diff --git a/src/safeds/ml/classification/metrics/__init__.py b/src/safeds/ml/classification/metrics/__init__.py
deleted file mode 100644
index 92079917a..000000000
--- a/src/safeds/ml/classification/metrics/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-from ._module_level_functions import accuracy
diff --git a/src/safeds/ml/classification/metrics/_module_level_functions.py b/src/safeds/ml/classification/metrics/_module_level_functions.py
deleted file mode 100644
index 6d2dd7c51..000000000
--- a/src/safeds/ml/classification/metrics/_module_level_functions.py
+++ /dev/null
@@ -1,21 +0,0 @@
-from safeds.data.tabular.containers import Column
-from sklearn.metrics import accuracy_score
-
-
-def accuracy(actual: Column, expected: Column) -> float:
-    """
-    Compare the expected column and the predicted column and returns the accuracy.
-
-    Parameters
-    ----------
-    actual : Column
-        The column containing estimated values.
-    expected : Column
-        The column containing expected values.
-
-    Returns
-    -------
-    accuracy : float
-        The calculated accuracy score. The percentage of equal data.
-    """
-    return accuracy_score(actual._data, expected._data)
diff --git a/src/safeds/ml/regression/_regressor.py b/src/safeds/ml/regression/_regressor.py
index a32c7f770..6d0ebb9b5 100644
--- a/src/safeds/ml/regression/_regressor.py
+++ b/src/safeds/ml/regression/_regressor.py
@@ -1,6 +1,9 @@
 from abc import ABC, abstractmethod
 
-from safeds.data.tabular.containers import Table, TaggedTable
+from safeds.data.tabular.containers import Column, Table, TaggedTable
+from safeds.exceptions import ColumnLengthMismatchError
+from sklearn.metrics import mean_absolute_error as sk_mean_absolute_error
+from sklearn.metrics import mean_squared_error as sk_mean_squared_error
 
 
 class Regressor(ABC):
@@ -44,3 +47,59 @@ def predict(self, dataset: Table) -> TaggedTable:
         PredictionError
             If prediction with the given dataset failed.
         """
+
+    def mean_squared_error(self, validation_or_test_set: TaggedTable) -> float:
+        """
+        Return the mean squared error, calculated from a given known truth and a column to compare.
+
+        Parameters
+        ----------
+        validation_or_test_set : TaggedTable
+            The validation or test set.
+
+        Returns
+        -------
+        mean_squared_error : float
+            The calculated mean squared error (the average of the distance of each individual row squared).
+        """
+
+        expected = validation_or_test_set.target
+        predicted = self.predict(validation_or_test_set.features).target
+
+        _check_metrics_preconditions(predicted, expected)
+        return sk_mean_squared_error(expected._data, predicted._data)
+
+    def mean_absolute_error(self, validation_or_test_set: TaggedTable) -> float:
+        """
+        Return the mean absolute error, calculated from a given known truth and a column to compare.
+
+        Parameters
+        ----------
+        validation_or_test_set : TaggedTable
+            The validation or test set.
+
+        Returns
+        -------
+        mean_absolute_error : float
+            The calculated mean absolute error (the average of the distance of each individual row).
+        """
+
+        expected = validation_or_test_set.target
+        predicted = self.predict(validation_or_test_set.features).target
+
+        _check_metrics_preconditions(predicted, expected)
+        return sk_mean_absolute_error(expected._data, predicted._data)
+
+
+def _check_metrics_preconditions(actual: Column, expected: Column) -> None:
+    if not actual.type.is_numeric():
+        raise TypeError(f"Column 'actual' is not numerical but {actual.type}.")
+    if not expected.type.is_numeric():
+        raise TypeError(f"Column 'expected' is not numerical but {expected.type}.")
+
+    if actual._data.size != expected._data.size:
+        raise ColumnLengthMismatchError(
+            "\n".join(
+                [f"{column.name}: {column._data.size}" for column in [actual, expected]]
+            )
+        )
diff --git a/src/safeds/ml/regression/metrics/__init__.py b/src/safeds/ml/regression/metrics/__init__.py
deleted file mode 100644
index c823ed790..000000000
--- a/src/safeds/ml/regression/metrics/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-from ._module_level_functions import mean_absolute_error, mean_squared_error
diff --git a/src/safeds/ml/regression/metrics/_module_level_functions.py b/src/safeds/ml/regression/metrics/_module_level_functions.py
deleted file mode 100644
index 0fc0d6d27..000000000
--- a/src/safeds/ml/regression/metrics/_module_level_functions.py
+++ /dev/null
@@ -1,58 +0,0 @@
-from safeds.data.tabular.containers import Column
-from safeds.exceptions import ColumnLengthMismatchError
-from sklearn.metrics import mean_absolute_error as mean_absolute_error_sklearn
-from sklearn.metrics import mean_squared_error as mean_squared_error_sklearn
-
-
-def mean_squared_error(actual: Column, expected: Column) -> float:
-    """
-    Return the mean squared error, calculated from a given known truth and a column to compare.
-
-    Parameters
-    ----------
-    actual : Column
-        The column containing estimated values.
-    expected : Column
-        The column containing ground truth.
-
-    Returns
-    -------
-    mean_squared_error : float
-        The calculated mean squared error (the average of the distance of each individual row squared).
-    """
-    _check_metrics_preconditions(actual, expected)
-    return mean_squared_error_sklearn(expected._data.tolist(), actual._data.tolist())
-
-
-def mean_absolute_error(actual: Column, expected: Column) -> float:
-    """
-    Return the mean absolute error, calculated from a given known truth and a column to compare.
-
-    Parameters
-    ----------
-    actual: Column
-        The column containing estimated values.
-    expected: Column
-        The column containing ground truth.
-
-    Returns
-    -------
-    mean_absolute_error : float
-        The calculated mean absolute error (the average of the distance of each individual row).
-    """
-    _check_metrics_preconditions(actual, expected)
-    return mean_absolute_error_sklearn(expected._data.tolist(), actual._data.tolist())
-
-
-def _check_metrics_preconditions(actual: Column, expected: Column) -> None:
-    if not actual.type.is_numeric():
-        raise TypeError(f"Column 'actual' is not numerical but {actual.type}.")
-    if not expected.type.is_numeric():
-        raise TypeError(f"Column 'expected' is not numerical but {expected.type}.")
-
-    if actual._data.size != expected._data.size:
-        raise ColumnLengthMismatchError(
-            "\n".join(
-                [f"{column.name}: {column._data.size}" for column in [actual, expected]]
-            )
-        )
diff --git a/tests/safeds/ml/classification/metrics/__init__.py b/tests/safeds/ml/classification/_classifier/__init__.py
similarity index 100%
rename from tests/safeds/ml/classification/metrics/__init__.py
rename to tests/safeds/ml/classification/_classifier/__init__.py
diff --git a/tests/safeds/ml/classification/_classifier/_dummy_classifier.py b/tests/safeds/ml/classification/_classifier/_dummy_classifier.py
new file mode 100644
index 000000000..60bb7859a
--- /dev/null
+++ b/tests/safeds/ml/classification/_classifier/_dummy_classifier.py
@@ -0,0 +1,26 @@
+from safeds.data.tabular.containers import Table, TaggedTable
+from safeds.ml.classification import Classifier
+
+
+class DummyClassifier(Classifier):
+    """
+    Dummy classifier to test metrics.
+
+    Metrics methods expect a `TaggedTable` as input with two columns:
+
+    - `predicted`: The predicted targets.
+    - `expected`: The correct targets.
+
+    `target_name` must be set to `"expected"`.
+    """
+
+    def fit(self, training_set: TaggedTable) -> None:
+        pass
+
+    def predict(self, dataset: Table) -> TaggedTable:
+        # Needed until https://github.com/Safe-DS/Stdlib/issues/75 is fixed
+        predicted = dataset.get_column("predicted")
+        feature = predicted.rename("feature")
+        dataset = Table.from_columns([feature, predicted])
+
+        return TaggedTable(dataset, target_name="predicted")
diff --git a/tests/safeds/ml/classification/_classifier/test_accuracy.py b/tests/safeds/ml/classification/_classifier/test_accuracy.py
new file mode 100644
index 000000000..ccb01bc32
--- /dev/null
+++ b/tests/safeds/ml/classification/_classifier/test_accuracy.py
@@ -0,0 +1,20 @@
+import pandas as pd
+from safeds.data.tabular.containers import Column, Table, TaggedTable
+
+from ._dummy_classifier import DummyClassifier
+
+
+def test_accuracy() -> None:
+    c1 = Column(pd.Series(data=[1, 2, 3, 4]), "predicted")
+    c2 = Column(pd.Series(data=[1, 2, 3, 3]), "expected")
+    table = TaggedTable(Table.from_columns([c1, c2]), target_name="expected")
+
+    assert DummyClassifier().accuracy(table) == 0.75
+
+
+def test_accuracy_different_types() -> None:
+    c1 = Column(pd.Series(data=["1", "2", "3", "4"]), "predicted")
+    c2 = Column(pd.Series(data=[1, 2, 3, 3]), "expected")
+    table = TaggedTable(Table.from_columns([c1, c2]), target_name="expected")
+
+    assert DummyClassifier().accuracy(table) == 0.0
diff --git a/tests/safeds/ml/classification/metrics/_accuracy/test_accuracy.py b/tests/safeds/ml/classification/metrics/_accuracy/test_accuracy.py
deleted file mode 100644
index 34aabf144..000000000
--- a/tests/safeds/ml/classification/metrics/_accuracy/test_accuracy.py
+++ /dev/null
@@ -1,15 +0,0 @@
-import pandas as pd
-from safeds.data.tabular.containers import Column
-from safeds.ml.classification.metrics import accuracy
-
-
-def test_accuracy() -> None:
-    c1 = Column(pd.Series(data=[1, 2, 3, 4]), "TestColumn1")
-    c2 = Column(pd.Series(data=[1, 2, 3, 3]), "TestColumn2")
-    assert accuracy(c1, c2) == 0.75
-
-
-def test_accuracy_different_types() -> None:
-    c1 = Column(pd.Series(data=["1", "2", "3", "4"]), "TestColumn1")
-    c2 = Column(pd.Series(data=[1, 2, 3, 3]), "TestColumn2")
-    assert accuracy(c1, c2) == 0.0
diff --git a/tests/safeds/ml/classification/metrics/_accuracy/__init__.py b/tests/safeds/ml/regression/_regressor/__init__.py
similarity index 100%
rename from tests/safeds/ml/classification/metrics/_accuracy/__init__.py
rename to tests/safeds/ml/regression/_regressor/__init__.py
diff --git a/tests/safeds/ml/regression/_regressor/_dummy_regressor.py b/tests/safeds/ml/regression/_regressor/_dummy_regressor.py
new file mode 100644
index 000000000..866a6ab6c
--- /dev/null
+++ b/tests/safeds/ml/regression/_regressor/_dummy_regressor.py
@@ -0,0 +1,26 @@
+from safeds.data.tabular.containers import Table, TaggedTable
+from safeds.ml.regression import Regressor
+
+
+class DummyRegressor(Regressor):
+    """
+    Dummy regressor to test metrics.
+
+    Metrics methods expect a `TaggedTable` as input with two columns:
+
+    - `predicted`: The predicted targets.
+    - `expected`: The correct targets.
+
+    `target_name` must be set to `"expected"`.
+    """
+
+    def fit(self, training_set: TaggedTable) -> None:
+        pass
+
+    def predict(self, dataset: Table) -> TaggedTable:
+        # Needed until https://github.com/Safe-DS/Stdlib/issues/75 is fixed
+        predicted = dataset.get_column("predicted")
+        feature = predicted.rename("feature")
+        dataset = Table.from_columns([feature, predicted])
+
+        return TaggedTable(dataset, target_name="predicted")
diff --git a/tests/safeds/ml/regression/metrics/test_check_metrics_preconditions.py b/tests/safeds/ml/regression/_regressor/test_check_metrics_preconditions.py
similarity index 87%
rename from tests/safeds/ml/regression/metrics/test_check_metrics_preconditions.py
rename to tests/safeds/ml/regression/_regressor/test_check_metrics_preconditions.py
index 924deaff5..d12ac6da6 100644
--- a/tests/safeds/ml/regression/metrics/test_check_metrics_preconditions.py
+++ b/tests/safeds/ml/regression/_regressor/test_check_metrics_preconditions.py
@@ -2,9 +2,9 @@
 import pytest
 from safeds.data.tabular.containers import Column
 from safeds.exceptions import ColumnLengthMismatchError
-from safeds.ml.regression.metrics._module_level_functions import (
-    _check_metrics_preconditions,
-)
+
+# noinspection PyProtectedMember
+from safeds.ml.regression._regressor import _check_metrics_preconditions
 
 
 @pytest.mark.parametrize(
diff --git a/tests/safeds/ml/regression/_regressor/test_mean_absolute_error.py b/tests/safeds/ml/regression/_regressor/test_mean_absolute_error.py
new file mode 100644
index 000000000..adb752264
--- /dev/null
+++ b/tests/safeds/ml/regression/_regressor/test_mean_absolute_error.py
@@ -0,0 +1,26 @@
+import pytest
+from safeds.data.tabular.containers import Column, Table, TaggedTable
+
+from ._dummy_regressor import DummyRegressor
+
+
+@pytest.mark.parametrize(
+    "predicted, expected, result",
+    [
+        ([1, 2], [1, 2], 0),
+        ([0, 0], [1, 1], 1),
+        ([1, 1, 1], [2, 2, 11], 4),
+        ([0, 0, 0], [10, 2, 18], 10),
+        ([0.5, 0.5], [1.5, 1.5], 1),
+    ],
+)
+def test_mean_absolute_error_valid(
+    predicted: list[float], expected: list[float], result: float
+) -> None:
+    predicted_column = Column(predicted, "predicted")
+    expected_column = Column(expected, "expected")
+    table = TaggedTable(
+        Table.from_columns([predicted_column, expected_column]), target_name="expected"
+    )
+
+    assert DummyRegressor().mean_absolute_error(table) == result
diff --git a/tests/safeds/ml/regression/_regressor/test_mean_squared_error.py b/tests/safeds/ml/regression/_regressor/test_mean_squared_error.py
new file mode 100644
index 000000000..27c85e2de
--- /dev/null
+++ b/tests/safeds/ml/regression/_regressor/test_mean_squared_error.py
@@ -0,0 +1,20 @@
+import pytest
+from safeds.data.tabular.containers import Column, Table, TaggedTable
+
+from ._dummy_regressor import DummyRegressor
+
+
+@pytest.mark.parametrize(
+    "predicted, expected, result",
+    [([1, 2], [1, 2], 0), ([0, 0], [1, 1], 1), ([1, 1, 1], [2, 2, 11], 34)],
+)
+def test_mean_squared_error_valid(
+    predicted: list[float], expected: list[float], result: float
+) -> None:
+    predicted_column = Column(predicted, "predicted")
+    expected_column = Column(expected, "expected")
+    table = TaggedTable(
+        Table.from_columns([predicted_column, expected_column]), target_name="expected"
+    )
+
+    assert DummyRegressor().mean_squared_error(table) == result
diff --git a/tests/safeds/ml/regression/metrics/test_mean_absolute_error.py b/tests/safeds/ml/regression/metrics/test_mean_absolute_error.py
deleted file mode 100644
index e97367762..000000000
--- a/tests/safeds/ml/regression/metrics/test_mean_absolute_error.py
+++ /dev/null
@@ -1,22 +0,0 @@
-import pandas as pd
-import pytest
-from safeds.data.tabular.containers import Column
-from safeds.ml.regression.metrics import mean_absolute_error
-
-
-@pytest.mark.parametrize(
-    "actual, expected, result",
-    [
-        ([1, 2], [1, 2], 0),
-        ([0, 0], [1, 1], 1),
-        ([1, 1, 1], [2, 2, 11], 4),
-        ([0, 0, 0], [10, 2, 18], 10),
-        ([0.5, 0.5], [1.5, 1.5], 1),
-    ],
-)
-def test_mean_absolute_error_valid(
-    actual: list[float], expected: list[float], result: float
-) -> None:
-    actual_column: Column = Column(pd.Series(actual), "actual")
-    expected_column: Column = Column(pd.Series(expected), "expected")
-    assert mean_absolute_error(actual_column, expected_column) == result
diff --git a/tests/safeds/ml/regression/metrics/test_mean_squared_error.py b/tests/safeds/ml/regression/metrics/test_mean_squared_error.py
deleted file mode 100644
index 19bd72c23..000000000
--- a/tests/safeds/ml/regression/metrics/test_mean_squared_error.py
+++ /dev/null
@@ -1,16 +0,0 @@
-import pandas as pd
-import pytest
-from safeds.data.tabular.containers import Column
-from safeds.ml.regression.metrics import mean_squared_error
-
-
-@pytest.mark.parametrize(
-    "actual, expected, result",
-    [([1, 2], [1, 2], 0), ([0, 0], [1, 1], 1), ([1, 1, 1], [2, 2, 11], 34)],
-)
-def test_mean_squared_error_valid(
-    actual: list[float], expected: list[float], result: float
-) -> None:
-    actual_column: Column = Column(pd.Series(actual), "actual")
-    expected_column: Column = Column(pd.Series(expected), "expected")
-    assert mean_squared_error(actual_column, expected_column) == result