diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 1eeed36875..e69f04926c 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -46,8 +46,9 @@ jobs:
         JIT=1 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_jitted.txt
     - name: Run 10 CIFAR training steps
       run: STEPS=10 python3 examples/hlb_cifar10.py | tee train_cifar.txt
-    - name: Run 10 CIFAR training steps w winograd
-      run: WINO=1 STEPS=10 python3 examples/hlb_cifar10.py | tee train_cifar_wino.txt
+    # TODO: this is flaky too
+    # - name: Run 10 CIFAR training steps w winograd
+    #   run: WINO=1 STEPS=10 python3 examples/hlb_cifar10.py | tee train_cifar_wino.txt
     - uses: actions/upload-artifact@v4
       with:
         name: Speed (Mac)