diff --git a/tests/config/evalp.toml b/tests/config/evalp.toml
index 8444d876ea1bb250060f4be116c46416d5eff32d..421e9ffc877483db3d44923350a3820a9f0510b0 100644
--- a/tests/config/evalp.toml
+++ b/tests/config/evalp.toml
@@ -4,7 +4,7 @@ metrics = ["BS", "BSS", "BS_CRD", "BS_LBD", "REL_DIAG", "CRPS_FROM_BS",
            "QS", "CRPS_FROM_QS",
            "POD", "POFD", "FAR", "CSI", "ROCSS",
            "RANK_HIST", "DS", "AS",
-           "CR", "AW", "AWN", "AWI", "WS", "WSS",
+           "CR", "AW", "AWN", "WS",
            "ES"]
 q_obs = "./data/evalp/obs"
 q_prd = "./data/evalp/prd"
diff --git a/tests/expected/evalp/AWI.csv b/tests/expected/evalp/AWI.csv
deleted file mode 100644
index 8b3b7e7f9598b23911dc06f440d71572b99b48e5..0000000000000000000000000000000000000000
--- a/tests/expected/evalp/AWI.csv
+++ /dev/null
@@ -1 +0,0 @@
-0.9821120161733,0.9880951944476
diff --git a/tests/expected/evalp/WSS.csv b/tests/expected/evalp/WSS.csv
deleted file mode 100644
index fd929dabd8f58354be587455dcbd4402d6a9f83d..0000000000000000000000000000000000000000
--- a/tests/expected/evalp/WSS.csv
+++ /dev/null
@@ -1 +0,0 @@
-0.6621887740287,0.4360388849930
diff --git a/tests/test_probabilist.py b/tests/test_probabilist.py
index 2c128fe910cf5efd249ab4722472ca4cf6464027..80a2b78f15270f1eb99dd95b1357113efae051a8 100644
--- a/tests/test_probabilist.py
+++ b/tests/test_probabilist.py
@@ -26,7 +26,7 @@ _all_metrics = (
     # ranks-based
     'RANK_HIST', 'DS', 'AS',
     # intervals-based
-    'CR', 'AW', 'AWN', 'AWI', 'WS', 'WSS',
+    'CR', 'AW', 'AWN', 'WS',
     # multivariate
     'ES'
 )
@@ -76,7 +76,7 @@ class TestMetrics(unittest.TestCase):
         metric: (
             numpy.genfromtxt(f"./expected/evalp/{metric}.csv", delimiter=',')
             [numpy.newaxis, numpy.newaxis, numpy.newaxis, numpy.newaxis, ...]
-        ) for metric in ('CR', 'AW', 'AWN', 'AWI', 'WS', 'WSS')
+        ) for metric in ('CR', 'AW', 'AWN', 'WS')
     }
 
     expected_mvr = {