diff --git a/pyproject.toml b/pyproject.toml
index 6bf242f07..a332f689a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,7 +10,7 @@ description = "ValidMind Library"
 license = "Commercial License"
 name = "validmind"
 readme = "README.pypi.md"
-version = "2.8.6"
+version = "2.8.7"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<3.12"
diff --git a/scripts/run_e2e_notebooks.py b/scripts/run_e2e_notebooks.py
index c2b45c3a6..81ded70e8 100644
--- a/scripts/run_e2e_notebooks.py
+++ b/scripts/run_e2e_notebooks.py
@@ -40,7 +40,7 @@
 
 NOTEBOOKS_TO_RUN = [
     "notebooks/code_samples/quickstart_customer_churn_full_suite.ipynb",
-    "notebooks/code_samples/time_series/quickstart_time_series_full_suite.ipynb",
+    "notebooks/code_samples/time_series/quickstart_time_series_high_code.ipynb",
     "notebooks/code_samples/regression/quickstart_regression_full_suite.ipynb",
     "notebooks/how_to/run_unit_metrics.ipynb",
     "notebooks/code_samples/custom_tests/integrate_external_test_providers.ipynb",
diff --git a/validmind/__version__.py b/validmind/__version__.py
index 261017211..c2c8ceb46 100644
--- a/validmind/__version__.py
+++ b/validmind/__version__.py
@@ -1 +1 @@
-__version__ = "2.8.6"
+__version__ = "2.8.7"
diff --git a/validmind/tests/comparison.py b/validmind/tests/comparison.py
index 0cacab0ba..6f94f8865 100644
--- a/validmind/tests/comparison.py
+++ b/validmind/tests/comparison.py
@@ -15,7 +15,7 @@
     is_png_image,
 )
 from validmind.vm_models.input import VMInput
-from validmind.vm_models.result import ResultTable, TestResult
+from validmind.vm_models.result import RawData, ResultTable, TestResult
 
 logger = get_logger(__name__)
 
@@ -312,6 +312,25 @@ def list_to_dict(grid_list):
     return test_configs
 
 
+def _combine_raw_data(results: List[TestResult]) -> RawData:
+    """Combine RawData objects"""
+    attribute_names = results[0].raw_data.__dict__.keys()
+
+    # check that all the raw data objects have the same attributes
+    for result in results:
+        if not isinstance(result.raw_data, RawData):
+            raise ValueError("All raw data objects must be of type RawData")
+        if result.raw_data.__dict__.keys() != attribute_names:
+            raise ValueError("RawData objects must have the same attributes")
+
+    return RawData(
+        **{
+            key: [getattr(result.raw_data, key) for result in results]
+            for key in attribute_names
+        }
+    )
+
+
 def combine_results(
     results: List[TestResult],
 ) -> Tuple[List[Any], Dict[str, List[Any]], Dict[str, List[Any]]]:
@@ -338,6 +357,9 @@ def combine_results(
     # handle threshold tests (i.e. tests that have pass/fail bool status)
     if results[0].passed is not None:
         combined_outputs.append(all(result.passed for result in results))
+    # handle raw data (if any)
+    if results[0].raw_data:
+        combined_outputs.append(_combine_raw_data(results))
 
     # combine inputs and params
     combined_inputs = {}
@@ -359,4 +381,8 @@ def combine_results(
     combined_inputs = _combine_dict_values(combined_inputs)
     combined_params = _combine_dict_values(combined_params)
 
-    return combined_outputs, combined_inputs, combined_params
+    return (
+        tuple(combined_outputs),
+        combined_inputs,
+        combined_params,
+    )
diff --git a/validmind/tests/run.py b/validmind/tests/run.py
index 610b9acd6..66dd40e7d 100644
--- a/validmind/tests/run.py
+++ b/validmind/tests/run.py
@@ -256,7 +256,7 @@ def _run_comparison_test(
     combined_outputs, combined_inputs, combined_params = combine_results(results)
 
     return build_test_result(
-        outputs=tuple(combined_outputs),
+        outputs=combined_outputs,
         test_id=test_id,
         test_doc=test_doc,
         inputs=combined_inputs,