diff --git a/doc/source/whatsnew/v1.3.0.rst b/doc/source/whatsnew/v1.3.0.rst
index 21e6f0ea57451..f735a1ffa16c3 100644
--- a/doc/source/whatsnew/v1.3.0.rst
+++ b/doc/source/whatsnew/v1.3.0.rst
@@ -754,6 +754,7 @@ Groupby/resample/rolling
 - Bug in :class:`core.window.ewm.ExponentialMovingWindow` when calling ``__getitem__`` would not retain ``com``, ``span``, ``alpha`` or ``halflife`` attributes  (:issue:`40164`)
 - :class:`core.window.ewm.ExponentialMovingWindow` now raises a ``NotImplementedError`` when specifying ``times`` with ``adjust=False`` due to an incorrect calculation (:issue:`40098`)
 - Bug in :meth:`Series.asfreq` and :meth:`DataFrame.asfreq` dropping rows when the index is not sorted (:issue:`39805`)
+- Bug in aggregation functions for :class:`DataFrame` not respecting ``numeric_only`` argument when ``level`` keyword was given (:issue:`40660`)
 
 Reshaping
 ^^^^^^^^^
@@ -809,7 +810,6 @@ Other
 - Bug in :func:`pandas.util.show_versions` where console JSON output was not proper JSON (:issue:`39701`)
 - Bug in :meth:`DataFrame.convert_dtypes` incorrectly raised ValueError when called on an empty DataFrame (:issue:`40393`)
 
-
 .. ---------------------------------------------------------------------------
 
 .. _whatsnew_130.contributors:
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index 4ef5aa1109074..ce1df8db82cb8 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -10493,7 +10493,9 @@ def _stat_function(
         if axis is None:
             axis = self._stat_axis_number
         if level is not None:
-            return self._agg_by_level(name, axis=axis, level=level, skipna=skipna)
+            return self._agg_by_level(
+                name, axis=axis, level=level, skipna=skipna, numeric_only=numeric_only
+            )
         return self._reduce(
             func, name=name, axis=axis, skipna=skipna, numeric_only=numeric_only
         )
@@ -10554,7 +10556,12 @@ def _min_count_stat_function(
             axis = self._stat_axis_number
         if level is not None:
             return self._agg_by_level(
-                name, axis=axis, level=level, skipna=skipna, min_count=min_count
+                name,
+                axis=axis,
+                level=level,
+                skipna=skipna,
+                min_count=min_count,
+                numeric_only=numeric_only,
             )
         return self._reduce(
             func,
diff --git a/pandas/tests/frame/test_reductions.py b/pandas/tests/frame/test_reductions.py
index 1304e861f948e..72f0787d69b22 100644
--- a/pandas/tests/frame/test_reductions.py
+++ b/pandas/tests/frame/test_reductions.py
@@ -1546,3 +1546,18 @@ def test_minmax_extensionarray(method, numeric_only):
         [getattr(int64_info, method)], index=Index(["Int64"], dtype="object")
     )
     tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("meth", ["max", "min", "sum", "mean", "median"])
+def test_groupy_regular_arithmetic_equivalent(meth):
+    # GH#40660
+    df = DataFrame(
+        {"a": [pd.Timedelta(hours=6), pd.Timedelta(hours=7)], "b": [12.1, 13.3]}
+    )
+    expected = df.copy()
+
+    result = getattr(df, meth)(level=0)
+    tm.assert_frame_equal(result, expected)
+
+    result = getattr(df.groupby(level=0), meth)(numeric_only=False)
+    tm.assert_frame_equal(result, expected)