diff --git a/test/external/external_model_benchmark.py b/test/external/external_model_benchmark.py
index 1efe9e5a1f..76ad4bd1bb 100644
--- a/test/external/external_model_benchmark.py
+++ b/test/external/external_model_benchmark.py
@@ -14,7 +14,8 @@ from tinygrad.ops import Device
 
 MODELS = {
   "resnet50": "https://github.com/onnx/models/raw/main/vision/classification/resnet/model/resnet50-caffe2-v1-9.onnx",
-  "openpilot": "https://github.com/commaai/openpilot/raw/v0.9.4/selfdrive/modeld/models/supercombo.onnx",
+  # broken in torch CPU
+  #"openpilot": "https://github.com/commaai/openpilot/raw/v0.9.4/selfdrive/modeld/models/supercombo.onnx",
   "efficientnet": "https://github.com/onnx/models/raw/main/vision/classification/efficientnet-lite4/model/efficientnet-lite4-11.onnx",
   "shufflenet": "https://github.com/onnx/models/raw/main/vision/classification/shufflenet/model/shufflenet-9.onnx",
   "commavq": "https://huggingface.co/commaai/commavq-gpt2m/resolve/main/gpt2m.onnx",