diff --git a/brainscore_vision/models/regnet/__init__.py b/brainscore_vision/models/regnet/__init__.py
new file mode 100644
index 000000000..0c95e6360
--- /dev/null
+++ b/brainscore_vision/models/regnet/__init__.py
@@ -0,0 +1,14 @@
+from brainscore_vision import model_registry
+from brainscore_vision.model_helpers.brain_transformation import ModelCommitment
+from .model import get_model, LAYERS
+
+BIBTEX = """@inproceedings{radosavovic2020designing,
+  title={Designing network design spaces},
+  author={Radosavovic, Ilija and Kosaraju, Raj Prateek and Girshick, Ross and He, Kaiming and Doll{\'a}r, Piotr},
+  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
+  pages={10428--10436},
+  year={2020}
+}"""
+
+model_registry['regnet_y_400mf'] = lambda: ModelCommitment(
+    identifier='regnet_y_400mf', activations_model=get_model(), layers=LAYERS)
diff --git a/brainscore_vision/models/regnet/model.py b/brainscore_vision/models/regnet/model.py
new file mode 100644
index 000000000..4690dbcbd
--- /dev/null
+++ b/brainscore_vision/models/regnet/model.py
@@ -0,0 +1,17 @@
+import functools
+
+import torchvision.models
+
+from brainscore_vision.model_helpers.activations.pytorch import PytorchWrapper
+from brainscore_vision.model_helpers.activations.pytorch import load_preprocess_images
+
+# these layer choices were not investigated in any depth, we blindly picked all high-level blocks
+LAYERS = ['trunk_output.block1', 'trunk_output.block2', 'trunk_output.block3', 'trunk_output.block4']
+
+
+def get_model():
+    model = torchvision.models.regnet_y_400mf(pretrained=True)
+    preprocessing = functools.partial(load_preprocess_images, image_size=224)
+    wrapper = PytorchWrapper(identifier='regnet_y_400mf', model=model, preprocessing=preprocessing)
+    wrapper.image_size = 224
+    return wrapper
diff --git a/brainscore_vision/models/regnet/test.py b/brainscore_vision/models/regnet/test.py
new file mode 100644
index 000000000..ad9c5b3bf
--- /dev/null
+++ b/brainscore_vision/models/regnet/test.py
@@ -0,0 +1,17 @@
+import logging
+import sys
+
+import pytest
+from pytest import approx
+
+from brainscore_vision import score
+
+logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+
+
+@pytest.mark.travis_slow
+@pytest.mark.memory_intense
+def test_score():
+    actual_score = score(model_identifier="regnet_y_400mf", benchmark_identifier="MajajHong2015public.IT-pls",
+                         conda_active=True)
+    assert actual_score == approx(0.532, abs=0.0005)