diff --git a/tests/test_cli.py b/tests/test_cli.py
index 7b58b03df9c3a5a516d590c40c1044412c8744bd..1b5ec0e45ac9be636b1e88cca08e2c01a7a54c16 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -154,12 +154,6 @@ def test_evaluate_help():
     _check_help(evaluate)
 
 
-def test_compare_help():
-    from ptbench.scripts.compare import compare
-
-    _check_help(compare)
-
-
 @pytest.mark.skip(reason="Test need to be updated")
 @pytest.mark.skip_if_rc_var_not_set("datadir.montgomery")
 def test_train_pasa_montgomery(temporary_basedir):
@@ -410,51 +404,6 @@ def test_evaluate_pasa_montgomery(temporary_basedir):
             )
 
 
-@pytest.mark.skip(reason="Test need to be updated")
-@pytest.mark.skip_if_rc_var_not_set("datadir.montgomery")
-def test_compare_pasa_montgomery(temporary_basedir):
-    from ptbench.scripts.compare import compare
-
-    runner = CliRunner()
-
-    with stdout_logging() as buf:
-        predictions_folder = str(temporary_basedir / "predictions")
-        output_folder = str(temporary_basedir / "comparisons")
-        result = runner.invoke(
-            compare,
-            [
-                "-vv",
-                "train",
-                f"{predictions_folder}/train/predictions.csv",
-                "test",
-                f"{predictions_folder}/test/predictions.csv",
-                f"--output-figure={output_folder}/compare.pdf",
-                f"--output-table={output_folder}/table.txt",
-                "--threshold=0.5",
-            ],
-        )
-        _assert_exit_0(result)
-
-        # check comparisons are there
-        assert os.path.exists(os.path.join(output_folder, "compare.pdf"))
-        assert os.path.exists(os.path.join(output_folder, "table.txt"))
-
-        keywords = {
-            r"^Dataset '\*': threshold =.*$": 1,
-            r"^Loading predictions from.*$": 2,
-            r"^Tabulating performance summary...": 1,
-        }
-        buf.seek(0)
-        logging_output = buf.read()
-
-        for k, v in keywords.items():
-            assert _str_counter(k, logging_output) == v, (
-                f"Count for string '{k}' appeared "
-                f"({_str_counter(k, logging_output)}) "
-                f"instead of the expected {v}:\nOutput:\n{logging_output}"
-            )
-
-
 @pytest.mark.skip(reason="Test need to be updated")
 @pytest.mark.skip_if_rc_var_not_set("datadir.montgomery")
 def test_train_mlp_montgomery_rs(temporary_basedir, datadir):