diff --git a/src/core/src/op/space_to_batch.cpp b/src/core/src/op/space_to_batch.cpp
index 57721c5e120472..b117a81ec2e056 100644
--- a/src/core/src/op/space_to_batch.cpp
+++ b/src/core/src/op/space_to_batch.cpp
@@ -102,7 +102,7 @@ bool ngraph::op::v1::SpaceToBatch::evaluate_space_to_batch(const HostTensorVecto
 
     auto data_shape = data->get_shape();
 
-    if (!(data->get_shape().size() == 4 || data->get_shape().size() == 5)) {
+    if (!(data->get_shape().size() == 3 || data->get_shape().size() == 4 || data->get_shape().size() == 5)) {
         return false;
     }
 
diff --git a/src/plugins/intel_gpu/src/plugin/ops/batch_to_space.cpp b/src/plugins/intel_gpu/src/plugin/ops/batch_to_space.cpp
index 6e243cc4aee4b2..a664ea02ff263f 100644
--- a/src/plugins/intel_gpu/src/plugin/ops/batch_to_space.cpp
+++ b/src/plugins/intel_gpu/src/plugin/ops/batch_to_space.cpp
@@ -31,7 +31,7 @@ static void CreateBatchToSpaceOp(Program& p, const std::shared_ptr<ngraph::op::v
 
         std::vector<int32_t> sizes = inConst->cast_vector<int32_t>();
         int32_t default_size = i == 1 ? 1 : 0;
-        for (size_t s = sizes.size(); s < rank; s++) {
+        for (size_t s = sizes.size(); s < format.dimension(); s++) {
             sizes.push_back(default_size);
         }
         tensor_inputs.emplace_back(format, sizes, default_size);
diff --git a/src/plugins/intel_gpu/src/plugin/ops/space_to_batch.cpp b/src/plugins/intel_gpu/src/plugin/ops/space_to_batch.cpp
index 0be31669c28575..bbf9e0797a9442 100644
--- a/src/plugins/intel_gpu/src/plugin/ops/space_to_batch.cpp
+++ b/src/plugins/intel_gpu/src/plugin/ops/space_to_batch.cpp
@@ -31,7 +31,7 @@ static void CreateSpaceToBatchOp(Program& p, const std::shared_ptr<ngraph::op::v
 
         std::vector<int32_t> sizes = inConst->cast_vector<int32_t>();
         int32_t default_size = i == 1 ? 1 : 0;
-        for (size_t s = sizes.size(); s < rank; s++) {
+        for (size_t s = sizes.size(); s < format.dimension(); s++) {
             sizes.push_back(default_size);
         }
         tensor_inputs.emplace_back(format, sizes, default_size);
@@ -41,14 +41,14 @@ static void CreateSpaceToBatchOp(Program& p, const std::shared_ptr<ngraph::op::v
     // To be removed once we enable internal shape infer for all operations
     auto out_size = output_pshape.is_static() ? tensor_from_dims(output_pshape.to_shape()) : cldnn::tensor();
 
-    auto batchToSpacePrim = cldnn::space_to_batch(layerName,
+    auto spaceToBatchPrim = cldnn::space_to_batch(layerName,
                                                   inputs[0], // input
                                                   tensor_inputs[0],          // block_shape
                                                   tensor_inputs[1],          // crops_begin
                                                   tensor_inputs[2],          // crops_end
                                                   out_size);
 
-    p.add_primitive(*op, batchToSpacePrim);
+    p.add_primitive(*op, spaceToBatchPrim);
 }
 
 REGISTER_FACTORY_IMPL(v1, SpaceToBatch);
diff --git a/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/batch_to_space.cpp b/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/batch_to_space.cpp
index 0d20838ac402e5..bff7e829448aea 100644
--- a/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/batch_to_space.cpp
+++ b/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/batch_to_space.cpp
@@ -11,7 +11,17 @@ using namespace LayerTestsDefinitions;
 
 namespace {
 auto bts_only_test_cases = []() {
-    return std::vector<batchToSpaceParamsTuple>{batchToSpaceParamsTuple({1, 1, 2, 2},
+    return std::vector<batchToSpaceParamsTuple>{batchToSpaceParamsTuple({1, 2, 2},
+                                                                        {0, 0, 0},
+                                                                        {0, 0, 0},
+                                                                        {4, 1, 1},
+                                                                        InferenceEngine::Precision::FP32,
+                                                                        InferenceEngine::Precision::UNSPECIFIED,
+                                                                        InferenceEngine::Precision::UNSPECIFIED,
+                                                                        InferenceEngine::Layout::ANY,
+                                                                        InferenceEngine::Layout::ANY,
+                                                                        CommonTestUtils::DEVICE_GPU),
+                                                batchToSpaceParamsTuple({1, 1, 2, 2},
                                                                         {0, 0, 0, 0},
                                                                         {0, 0, 0, 0},
                                                                         {4, 1, 1, 1},
diff --git a/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/space_to_batch.cpp b/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/space_to_batch.cpp
index 1ad03e2015187d..0a78ecff4622cb 100644
--- a/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/space_to_batch.cpp
+++ b/src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/space_to_batch.cpp
@@ -13,6 +13,16 @@ namespace {
 
 auto stb_only_test_cases = []() {
     return std::vector<spaceToBatchParamsTuple>{
+        spaceToBatchParamsTuple({1, 2, 2},
+                                {0, 0, 0},
+                                {0, 0, 0},
+                                {1, 2, 2},
+                                InferenceEngine::Precision::FP32,
+                                InferenceEngine::Precision::UNSPECIFIED,
+                                InferenceEngine::Precision::UNSPECIFIED,
+                                InferenceEngine::Layout::ANY,
+                                InferenceEngine::Layout::ANY,
+                                CommonTestUtils::DEVICE_GPU),
         spaceToBatchParamsTuple({1, 1, 2, 2},
                                 {0, 0, 0, 0},
                                 {0, 0, 0, 0},
diff --git a/src/plugins/template/tests/functional/op_reference/batch_to_space.cpp b/src/plugins/template/tests/functional/op_reference/batch_to_space.cpp
index e9f5ce61384d63..7c8da263b078fd 100644
--- a/src/plugins/template/tests/functional/op_reference/batch_to_space.cpp
+++ b/src/plugins/template/tests/functional/op_reference/batch_to_space.cpp
@@ -90,6 +90,15 @@ std::vector<BatchToSpaceParams> generateBatchToSpaceParams() {
             reference_tests::Tensor({2, 6}, IN_ET, std::vector<T>{1, 7, 2, 8, 3, 9, 4, 10, 5, 11, 6, 12}),
             "input_with_shape_4x3"),
 
+        // input_with_shape_4x1x3
+        BatchToSpaceParams(
+            reference_tests::Tensor({4, 1, 3}, IN_ET, std::vector<T>{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12}),
+            reference_tests::Tensor({3}, element::i64, std::vector<int64_t>{1, 1, 2}),
+            reference_tests::Tensor({3}, element::i64, std::vector<int64_t>{0, 0, 0}),
+            reference_tests::Tensor({3}, element::i64, std::vector<int64_t>{0, 0, 0}),
+            reference_tests::Tensor({2, 1, 6}, IN_ET, std::vector<T>{1, 7, 2, 8, 3, 9, 4, 10, 5, 11, 6, 12}),
+            "input_with_shape_4x1x3"),
+
         // input_with_shape_4x1x1x3
         BatchToSpaceParams(
             reference_tests::Tensor({4, 1, 1, 3}, IN_ET, std::vector<T>{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12}),
diff --git a/src/plugins/template/tests/functional/op_reference/space_to_batch.cpp b/src/plugins/template/tests/functional/op_reference/space_to_batch.cpp
index 38210a96d95114..cbfe36d6963f30 100644
--- a/src/plugins/template/tests/functional/op_reference/space_to_batch.cpp
+++ b/src/plugins/template/tests/functional/op_reference/space_to_batch.cpp
@@ -82,6 +82,15 @@ template <element::Type_t IN_ET>
 std::vector<SpaceToBatchParams> generateParams() {
     using T = typename element_type_traits<IN_ET>::value_type;
     std::vector<SpaceToBatchParams> batchToSpaceParams {
+        // space_to_batch_3D
+        SpaceToBatchParams(
+            reference_tests::Tensor({1, 2, 2}, IN_ET, std::vector<T>{1, 1, 1, 1}),
+            reference_tests::Tensor({3}, element::i64, std::vector<int64_t>{1, 1, 1}),
+            reference_tests::Tensor({3}, element::i64, std::vector<int64_t>{0, 0, 0}),
+            reference_tests::Tensor({3}, element::i64, std::vector<int64_t>{0, 0, 0}),
+            reference_tests::Tensor({1, 2, 2}, IN_ET, std::vector<T>{1, 1, 1, 1}),
+            "space_to_batch_4D"),
+
         // space_to_batch_4D
         SpaceToBatchParams(
             reference_tests::Tensor({1, 1, 2, 2}, IN_ET, std::vector<T>{1, 1, 1, 1}),