diff --git a/src/backends/neon/workloads/CMakeLists.txt b/src/backends/neon/workloads/CMakeLists.txt
index 1a1ed74..31b0866 100644
--- a/src/backends/neon/workloads/CMakeLists.txt
+++ b/src/backends/neon/workloads/CMakeLists.txt
@@ -24,6 +24,8 @@
     NeonFloorFloatWorkload.hpp
     NeonFullyConnectedWorkload.cpp
     NeonFullyConnectedWorkload.hpp
+    NeonGreaterWorkload.cpp
+    NeonGreaterWorkload.hpp
     NeonL2NormalizationFloatWorkload.cpp
     NeonL2NormalizationFloatWorkload.hpp
     NeonLstmFloatWorkload.cpp
diff --git a/src/backends/neon/workloads/NeonGreaterWorkload.cpp b/src/backends/neon/workloads/NeonGreaterWorkload.cpp
new file mode 100644
index 0000000..ece52d6
--- /dev/null
+++ b/src/backends/neon/workloads/NeonGreaterWorkload.cpp
@@ -0,0 +1,49 @@
+//
+// Copyright © 2017 Arm Ltd. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#include "NeonGreaterWorkload.hpp"
+#include <aclCommon/ArmComputeTensorUtils.hpp>
+#include <backendsCommon/CpuTensorHandle.hpp>
+
+namespace armnn
+{
+
+arm_compute::Status NeonGreaterWorkloadValidate(const TensorInfo& input0,
+                                                const TensorInfo& input1,
+                                                const TensorInfo& output)
+{
+    const arm_compute::TensorInfo aclInput0 = armcomputetensorutils::BuildArmComputeTensorInfo(input0);
+    const arm_compute::TensorInfo aclInput1 = armcomputetensorutils::BuildArmComputeTensorInfo(input1);
+    const arm_compute::TensorInfo aclOutput = armcomputetensorutils::BuildArmComputeTensorInfo(output);
+
+    return arm_compute::NEGreater::validate(&aclInput0,
+                                            &aclInput1,
+                                            &aclOutput);
+}
+
+template <DataType T>
+NeonGreaterWorkload<T>::NeonGreaterWorkload(const GreaterQueueDescriptor& descriptor, const WorkloadInfo& info)
+    : MultiTypedWorkload<GreaterQueueDescriptor, T, DataType::Boolean>(descriptor, info)
+{
+    m_Data.ValidateInputsOutputs("NeonGreaterWorkload", 2, 1);
+
+    arm_compute::ITensor& input0 = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
+    arm_compute::ITensor& input1 = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Inputs[1])->GetTensor();
+    arm_compute::ITensor& output = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
+
+    m_GreaterLayer.configure(&input0, &input1, &output);
+}
+
+template <DataType T>
+void NeonGreaterWorkload<T>::Execute() const
+{
+    ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonGreaterWorkload_Execute");
+    m_GreaterLayer.run();
+}
+
+template class NeonGreaterWorkload<DataType::Float32>;
+template class NeonGreaterWorkload<DataType::QuantisedAsymm8>;
+
+} //namespace armnn
\ No newline at end of file
diff --git a/src/backends/neon/workloads/NeonGreaterWorkload.hpp b/src/backends/neon/workloads/NeonGreaterWorkload.hpp
new file mode 100644
index 0000000..df1e07e
--- /dev/null
+++ b/src/backends/neon/workloads/NeonGreaterWorkload.hpp
@@ -0,0 +1,36 @@
+//
+// Copyright © 2017 Arm Ltd. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#pragma once
+
+#include <neon/workloads/NeonWorkloadUtils.hpp>
+
+#include <arm_compute/runtime/NEON/functions/NEElementwiseOperations.h>
+
+namespace armnn
+{
+
+arm_compute::Status NeonGreaterWorkloadValidate(const TensorInfo& input0,
+                                                const TensorInfo& input1,
+                                                const TensorInfo& output);
+
+template <DataType T>
+class NeonGreaterWorkload : public MultiTypedWorkload<GreaterQueueDescriptor, T, DataType::Boolean>
+{
+public:
+    using MultiTypedWorkload<GreaterQueueDescriptor, T, DataType::Boolean>::m_Data;
+
+    NeonGreaterWorkload(const GreaterQueueDescriptor& descriptor, const WorkloadInfo& info);
+
+    virtual void Execute() const override;
+
+private:
+    mutable arm_compute::NEGreater m_GreaterLayer;
+};
+
+using NeonGreaterFloat32Workload = NeonGreaterWorkload<DataType::Float32>;
+using NeonGreaterUint8Workload = NeonGreaterWorkload<DataType::QuantisedAsymm8>;
+
+} //namespace armnn
\ No newline at end of file
diff --git a/src/backends/neon/workloads/NeonWorkloads.hpp b/src/backends/neon/workloads/NeonWorkloads.hpp
index e4f4fcf..af85eb2 100644
--- a/src/backends/neon/workloads/NeonWorkloads.hpp
+++ b/src/backends/neon/workloads/NeonWorkloads.hpp
@@ -14,6 +14,7 @@
 #include "NeonDepthwiseConvolutionWorkload.hpp"
 #include "NeonFloorFloatWorkload.hpp"
 #include "NeonFullyConnectedWorkload.hpp"
+#include "NeonGreaterWorkload.hpp"
 #include "NeonL2NormalizationFloatWorkload.hpp"
 #include "NeonLstmFloatWorkload.hpp"
 #include "NeonMaximumWorkload.hpp"