diff --git a/src/modelskill/metrics.py b/src/modelskill/metrics.py
index 5d0652666..6ea0838d6 100644
--- a/src/modelskill/metrics.py
+++ b/src/modelskill/metrics.py
@@ -251,6 +251,9 @@ def nash_sutcliffe_efficiency(obs: ArrayLike, model: ArrayLike) -> Any:
 
     Nash, J. E.; Sutcliffe, J. V. (1970). "River flow forecasting through conceptual models part I — A discussion of principles". Journal of Hydrology. 10 (3): 282–290. <https://doi.org/10.1016/0022-1694(70)90255-6>
     """
+    # np.sum on a pandas Series skips NaN, so convert to get NaN like the other metrics
+    obs = np.asarray(obs)
+    model = np.asarray(model)
     assert obs.size == model.size
 
     if len(obs) == 0:
@@ -331,6 +334,9 @@ def r2(obs: ArrayLike, model: ArrayLike) -> Any:
     >>> r2(obs,model)
     np.float64(0.6379999999999998)
     """
+    # np.sum on a pandas Series skips NaN, so convert to get NaN like the other metrics
+    obs = np.asarray(obs)
+    model = np.asarray(model)
     assert obs.size == model.size
     if len(obs) == 0:
         return np.nan
diff --git a/tests/test_metrics.py b/tests/test_metrics.py
index 26bc58579..89a675042 100644
--- a/tests/test_metrics.py
+++ b/tests/test_metrics.py
@@ -74,6 +74,19 @@ def test_kge_climatology_model():
     assert mtr.kling_gupta_efficiency(obs, mod) == pytest.approx(-0.41, abs=1e-2)
 
 
+@pytest.mark.parametrize("metric", [mtr.nse, mtr.r2])
+@pytest.mark.parametrize(
+    "model", [[1.0, 2.0, np.nan, np.nan], [np.nan, np.nan, np.nan, np.nan]]
+)
+def test_nse_r2_nan_in_model_series(metric: Callable, model: list) -> None:
+    # pandas Series must give the same result as NumPy arrays (NaN), not 1.0
+    obs = pd.Series([1.0, 2.0, 3.0, 4.0])
+    mod = pd.Series(model)
+
+    assert np.isnan(metric(obs.to_numpy(), mod.to_numpy()))
+    assert np.isnan(metric(obs, mod))
+
+
 def test_nse_suboptimal():
     obs = np.array([1.0, 0.5, 0])
     mod = np.array([1.0, 0.0, 0.5])