diff --git a/gtsam/hybrid/HybridBayesNet.cpp b/gtsam/hybrid/HybridBayesNet.cpp
index 59dfd809d..772fb250c 100644
--- a/gtsam/hybrid/HybridBayesNet.cpp
+++ b/gtsam/hybrid/HybridBayesNet.cpp
@@ -347,8 +347,6 @@ HybridGaussianFactorGraph HybridBayesNet::toFactorGraph(
         fg.push_back(gc->likelihood(measurements));
       } else if (auto gm = conditional->asMixture()) {
         fg.push_back(gm->likelihood(measurements));
-        const auto constantsFactor = gm->normalizationConstants();
-        if (constantsFactor) fg.push_back(constantsFactor);
       } else {
         throw std::runtime_error("Unknown conditional type");
       }
diff --git a/gtsam/hybrid/tests/testHybridBayesNet.cpp b/gtsam/hybrid/tests/testHybridBayesNet.cpp
index 1feabc4b5..da16299a8 100644
--- a/gtsam/hybrid/tests/testHybridBayesNet.cpp
+++ b/gtsam/hybrid/tests/testHybridBayesNet.cpp
@@ -77,9 +77,17 @@ TEST(HybridBayesNet, Tiny) {
   auto bn = tiny::createHybridBayesNet();
   EXPECT_LONGS_EQUAL(3, bn.size());
 
-  const VectorValues measurements{{Z(0), Vector1(5.0)}};
-  auto fg = bn.toFactorGraph(measurements);
-  EXPECT_LONGS_EQUAL(4, fg.size());
+  const VectorValues vv{{Z(0), Vector1(5.0)}, {X(0), Vector1(5.0)}};
+  auto fg = bn.toFactorGraph(vv);
+  EXPECT_LONGS_EQUAL(3, fg.size());
+
+  // Check that the ratio of probPrime to evaluate is the same for all modes.
+  std::vector<double> ratio(2);
+  for (size_t mode : {0, 1}) {
+    const HybridValues hv{vv, {{M(0), mode}}};
+    ratio[mode] = std::exp(-fg.error(hv)) / bn.evaluate(hv);
+  }
+  EXPECT_DOUBLES_EQUAL(ratio[0], ratio[1], 1e-8);
 }
 
 /* ****************************************************************************/