diff --git a/docs/OperatorKernels.md b/docs/OperatorKernels.md
index 1dbda4aeff..c76f760ef0 100644
--- a/docs/OperatorKernels.md
+++ b/docs/OperatorKernels.md
@@ -350,7 +350,8 @@ Do not modify directly.*
 |SimplifiedLayerNormalization|*in* X:**T**<br> *in* scale:**V**<br> *out* Y:**V**<br> *out* inv_std_var:**U**|1+|**T** = tensor(double), tensor(float)<br/> **U** = tensor(double), tensor(float)<br/> **V** = tensor(double), tensor(float)|
 |Sin|*in* input:**T**<br> *out* output:**T**|7+|**T** = tensor(double), tensor(float)|
 |Sinh|*in* input:**T**<br> *out* output:**T**|9+|**T** = tensor(float)|
-|Size|*in* data:**T**<br> *out* size:**T1**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(int64)|
+|Size|*in* data:**T**<br> *out* size:**T1**|19+|**T** = tensor(bool), tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(int64)|
+|||[13, 18]|**T** = tensor(bool), tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(int64)|
 |||[1, 12]|**T** = tensor(bool), tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(int64)|
 |Slice|*in* data:**T**<br> *in* starts:**Tind**<br> *in* ends:**Tind**<br> *in* axes:**Tind**<br> *in* steps:**Tind**<br> *out* output:**T**<br><br>or<br><br>*in* data:**T**<br> *out* output:**T**|13+|**T** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
 |||[11, 12]|**T** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
diff --git a/onnxruntime/core/providers/cpu/cpu_execution_provider.cc b/onnxruntime/core/providers/cpu/cpu_execution_provider.cc
index ffdb66f84c..18010960e1 100644
--- a/onnxruntime/core/providers/cpu/cpu_execution_provider.cc
+++ b/onnxruntime/core/providers/cpu/cpu_execution_provider.cc
@@ -581,7 +581,7 @@ class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOn
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, 18, int8_t, QuantizeLinear);
 class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, Sigmoid);
 class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, Sign);
-class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, Size);
+class ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, 18, Size);
 class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, float, Sum);
 class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, double, Sum);
 class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, Flatten);
@@ -917,6 +917,7 @@ class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 18, Op
 #endif
 
 // Opset 19
+class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 19, Size);
 class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 19, AveragePool);
 #ifdef MLAS_F16VEC_INTRINSICS_SUPPORTED
 class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 19, MLFloat16, AveragePool);
@@ -1815,7 +1816,7 @@ Status RegisterOnnxOperatorKernels(KernelRegistry& kernel_registry) {
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, float, Gemm)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, double, Gemm)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, Sign)>,
-    BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, Size)>,
+    BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, 18, Size)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, float, Sum)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, double, Sum)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 13, float, Sigmoid)>,
@@ -2332,6 +2333,7 @@ Status RegisterOnnxOperatorKernels(KernelRegistry& kernel_registry) {
 #endif
 
     // Opset 19
+    BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 19, Size)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 19, AveragePool)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 19, Cast)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 19, uint8_t,
diff --git a/onnxruntime/core/providers/cpu/tensor/size.cc b/onnxruntime/core/providers/cpu/tensor/size.cc
index 47dbee0113..9d9862b4ce 100644
--- a/onnxruntime/core/providers/cpu/tensor/size.cc
+++ b/onnxruntime/core/providers/cpu/tensor/size.cc
@@ -45,9 +45,28 @@ ONNX_CPU_OPERATOR_VERSIONED_KERNEL(
         .TypeConstraint("T1", DataTypeImpl::GetTensorType<int64_t>()),
     Size);
 
+ONNX_CPU_OPERATOR_VERSIONED_KERNEL(
+    Size,
+    13, 18,
+    KernelDefBuilder().TypeConstraint("T",
+                                      std::vector<MLDataType>({DataTypeImpl::GetTensorType<float>(),
+                                                               DataTypeImpl::GetTensorType<double>(),
+                                                               DataTypeImpl::GetTensorType<int8_t>(),
+                                                               DataTypeImpl::GetTensorType<int16_t>(),
+                                                               DataTypeImpl::GetTensorType<int32_t>(),
+                                                               DataTypeImpl::GetTensorType<int64_t>(),
+                                                               DataTypeImpl::GetTensorType<uint8_t>(),
+                                                               DataTypeImpl::GetTensorType<uint16_t>(),
+                                                               DataTypeImpl::GetTensorType<uint32_t>(),
+                                                               DataTypeImpl::GetTensorType<uint64_t>(),
+                                                               DataTypeImpl::GetTensorType<std::string>(),
+                                                               DataTypeImpl::GetTensorType<bool>()}))
+        .TypeConstraint("T1", DataTypeImpl::GetTensorType<int64_t>()),
+    Size);
+
 ONNX_CPU_OPERATOR_KERNEL(
     Size,
-    13,
+    19,
     KernelDefBuilder().TypeConstraint("T",
                                       std::vector<MLDataType>({DataTypeImpl::GetTensorType<float>(),
                                                                DataTypeImpl::GetTensorType<double>(),
diff --git a/onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc b/onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc
index 014af80e0e..71a10f646a 100644
--- a/onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc
+++ b/onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc
@@ -196,8 +196,6 @@
         "^test_reshape_reordered_last_dims*",
         "^test_reshape_zero_and_negative_dim*",
         "^test_reshape_zero_dim*",
-        "^test_size*",
-        "^test_size_example*",
         // TODO: fialures with Windows GPU CI Pipeline that are introduced with ONNX opset 19. Need to be fixed before ORT 1.15 release.
         "^test_averagepool_*",
         "^test_wrap_pad_cuda",