diff --git a/.github/workflows/examples.yml b/.github/workflows/examples.yml
index 7622139892..0d5a0fcf45 100644
--- a/.github/workflows/examples.yml
+++ b/.github/workflows/examples.yml
@@ -75,7 +75,7 @@ jobs:
 
       - name: Run example tests
         working-directory: autotest
-        run: pytest -v test_example_scripts.py -n=auto -s --durations=0 --keep-failed=.failed
+        run: pytest -v test_example_notebooks.py -n=auto -s --durations=0 --keep-failed=.failed
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
diff --git a/autotest/test_example_notebooks.py b/autotest/test_example_notebooks.py
index ad59e1b1e2..04654a9648 100644
--- a/autotest/test_example_notebooks.py
+++ b/autotest/test_example_notebooks.py
@@ -44,6 +44,7 @@ def test_notebooks(notebook):
             pkg = re.findall("No module named '(.*)'", stderr)[0]
             pytest.skip(f"notebook requires package {pkg!r}")
 
-    assert returncode == 0, f"could not run {notebook}"
-    pprint(stdout)
-    pprint(stderr)
+    if returncode != 0:
+        pprint(stdout)
+        pprint(stderr)
+        raise ValueError(f"could not run {notebook}")
diff --git a/autotest/test_example_scripts.py b/autotest/test_example_scripts.py
deleted file mode 100644
index 56909c53fa..0000000000
--- a/autotest/test_example_scripts.py
+++ /dev/null
@@ -1,48 +0,0 @@
-import re
-from pprint import pprint
-
-import pytest
-from flaky import flaky
-from modflow_devtools.misc import is_in_ci, run_cmd, run_py_script
-
-from autotest.conftest import get_project_root_path
-
-
-def get_scripts(pattern=None, exclude=None):
-    prjroot = get_project_root_path()
-    nbpaths = [
-        str(p)
-        for p in (prjroot / ".docs" / "Notebooks").glob("*.py")
-        if pattern is None or pattern in p.name
-    ]
-
-    # sort for pytest-xdist: workers must collect tests in the same order
-    return sorted(
-        [p for p in nbpaths if not exclude or not any(e in p for e in exclude)]
-    )
-
-
-@flaky(max_runs=3)
-@pytest.mark.slow
-@pytest.mark.example
-@pytest.mark.parametrize(
-    "script",
-    get_scripts(pattern="tutorial", exclude=["mf6_lgr"])
-    + get_scripts(pattern="example"),
-)
-def test_scripts(script):
-    stdout, stderr, returncode = run_py_script(script, verbose=True)
-
-    # allow notebooks to fail for lack of optional dependencies in local runs,
-    # expect all dependencies to be present and notebooks to pass in ci tests.
-    if returncode != 0 and not is_in_ci():
-        if "Missing optional dependency" in stderr:
-            pkg = re.findall("Missing optional dependency '(.*)'", stderr)[0]
-            pytest.skip(f"notebook requires optional dependency {pkg!r}")
-        elif "No module named " in stderr:
-            pkg = re.findall("No module named '(.*)'", stderr)[0]
-            pytest.skip(f"notebook requires package {pkg!r}")
-
-    assert returncode == 0, f"could not run {script}"
-    pprint(stdout)
-    pprint(stderr)