diff --git a/.github/workflows/test_iree.yml b/.github/workflows/test_iree.yml
index 97c563785..6f9003a84 100644
--- a/.github/workflows/test_iree.yml
+++ b/.github/workflows/test_iree.yml
@@ -81,4 +81,4 @@ jobs:
         run: |
           source ${VENV_DIR}/bin/activate
           pytest iree_tests -s -n auto -k real_weights -rpfE --timeout=1200 --retries 2 --retry-delay 5 --durations=0
-          pytest iree_tests/benchmarks -n auto -rpfE --timeout=6000 --durations=0
+          pytest iree_tests/benchmarks -s -rpfE --timeout=6000 --durations=0
diff --git a/iree_tests/benchmarks/sdxl_benchmark/model.mlirbc b/iree_tests/benchmarks/sdxl-benchmark/model.mlirbc
similarity index 100%
rename from iree_tests/benchmarks/sdxl_benchmark/model.mlirbc
rename to iree_tests/benchmarks/sdxl-benchmark/model.mlirbc
diff --git a/iree_tests/benchmarks/sdxl_benchmark/test_data_flags.txt b/iree_tests/benchmarks/sdxl-benchmark/test_data_flags.txt
similarity index 100%
rename from iree_tests/benchmarks/sdxl_benchmark/test_data_flags.txt
rename to iree_tests/benchmarks/sdxl-benchmark/test_data_flags.txt
diff --git a/iree_tests/conftest.py b/iree_tests/conftest.py
index 0f5fa5f9a..c28fac23c 100644
--- a/iree_tests/conftest.py
+++ b/iree_tests/conftest.py
@@ -283,10 +283,14 @@ def __init__(self, spec, **kwargs):
 
         # TODO(scotttodd): swap cwd for a temp path?
         self.test_cwd = self.spec.test_directory
+        print("CWD: " + str(self.test_cwd))
         vae_decode_path = os.path.dirname(os.path.dirname(self.test_cwd)) + "/pytorch/models/sdxl-vae-decode-tank"
         scheduled_unet_path = os.path.dirname(os.path.dirname(self.test_cwd)) + "/pytorch/models/sdxl-scheduled-unet-tank"
         prompt_encoder_path = os.path.dirname(os.path.dirname(self.test_cwd)) + "/pytorch/models/sdxl-prompt-encoder-tank"
         vmfb_name = f"{self.spec.input_mlir_stem}_{self.spec.test_name}.vmfb"
+        print("VAE: " + str(vae_decode_path))
+        print("UNET: " + str(scheduled_unet_path))
+        print("CLIP: " + str(prompt_encoder_path))
 
         self.compile_args = ["iree-compile", self.spec.input_mlir_name]
         self.compile_args.extend(self.spec.iree_compile_flags)
@@ -323,8 +327,9 @@ def runtest(self):
                     reason="Expected run to fail",
                 )
             )
-        self.test_run()
-        if self.spec.test_directory.name == "sdxl-pipeline-benchmark":
+        # self.test_run()
+        print("TEST DIR NAME: " + str(self.spec.test_directory.name))
+        if self.spec.test_directory.name == "sdxl-benchmark":
             self.test_benchmark()
         else:
             self.test_run()