diff --git a/Experiments/evaluate_metrics.py b/Experiments/evaluate_metrics.py
index 599dd94c61d34f273d4403c76d4dbe6b04ebdc5c..b415792857ac162211827b13f5e7a567a08f8fc6 100644
--- a/Experiments/evaluate_metrics.py
+++ b/Experiments/evaluate_metrics.py
@@ -139,6 +139,8 @@ def collect_metrics(x_y_pairs, seed=0,
                 epistemic_coverage(not_averaged_predictions, true_y,
                         average_predictions=True,
                         normalize_errors=False, noisy_y=False)
+    true_res = true_y - noneiv_mean
+    noneiv_metrics['true_rmse'] = np.sqrt(np.mean(scaled_res**2))
 
 
     # NLL
@@ -208,7 +210,8 @@ def collect_metrics(x_y_pairs, seed=0,
                         average_predictions=True,
                         normalize_errors=False, noisy_y=False)
 
-
+    true_res = true_y - eiv_mean
+    eiv_metrics['true_rmse'] = np.sqrt(np.mean(scaled_res**2))
 
     # NLL
     if scale_outputs: