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 c3adb76e0735535f7d240cd47e2566617fd84d8c..c47aaf29ebf8689d3695d9ff323c952f9af2c6af 100644
--- a/tests/test_probabilist.py
+++ b/tests/test_probabilist.py
@@ -24,7 +24,7 @@ _all_metrics = (
     # ranks-based
     'RANK_HIST', 'DS', 'AS',
     # intervals
-    'CR', 'AW', 'AWN', 'AWI', 'WS', 'WSS',
+    'CR', 'AW', 'AWN', 'WS',
     # multivariate
     'ES'
 )
@@ -82,7 +82,7 @@ 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 = {