diff --git a/tests/v1/e2e/test_spec_decode.py b/tests/v1/e2e/test_spec_decode.py
index 0b240b7d434e..bf90f50b1082 100644
--- a/tests/v1/e2e/test_spec_decode.py
+++ b/tests/v1/e2e/test_spec_decode.py
@@ -117,9 +117,9 @@ def test_ngram_correctness(
                 print(f"ref_output: {ref_output.outputs[0].text}")
                 print(f"spec_output: {spec_output.outputs[0].text}")
 
-        # Heuristic: expect at least 68% of the prompts to match exactly
+        # Heuristic: expect at least 66% of the prompts to match exactly
         # Upon failure, inspect the outputs to check for inaccuracy.
-        assert matches >= int(0.68 * len(ref_outputs))
+        assert matches >= int(0.66 * len(ref_outputs))
         del spec_llm
         torch.cuda.empty_cache()
         cleanup_dist_env_and_memory()