diff --git a/asv_bench/benchmarks/groupby.py b/asv_bench/benchmarks/groupby.py
index 4c0f3ddd826b7..bcf23ce43a820 100644
--- a/asv_bench/benchmarks/groupby.py
+++ b/asv_bench/benchmarks/groupby.py
@@ -71,7 +71,7 @@ def time_groupby_apply_dict_return(self):
 
 class Apply:
     param_names = ["factor"]
-    params = [4, 5]
+    params = [5, 6]
 
     def setup(self, factor):
         N = 10**factor
@@ -91,6 +91,7 @@ def setup(self, factor):
             }
         )
         self.df = df
+        self.df_sorted = df.sort_values(by="key")
 
     def time_scalar_function_multi_col(self, factor):
         self.df.groupby(["key", "key2"]).apply(lambda x: 1)
@@ -98,6 +99,24 @@ def time_scalar_function_multi_col(self, factor):
     def time_scalar_function_single_col(self, factor):
         self.df.groupby("key").apply(lambda x: 1)
 
+    def peakmem_scalar_function_multi_col(self, factor):
+        self.df.groupby(["key", "key2"]).apply(lambda x: 1)
+
+    def peakmem_scalar_function_single_col(self, factor):
+        self.df.groupby("key").apply(lambda x: 1)
+
+    def time_sorted_scalar_function_multi_col(self, factor):
+        self.df_sorted.groupby(["key", "key2"]).apply(lambda x: 1)
+
+    def time_sortedscalar_function_single_col(self, factor):
+        self.df_sorted.groupby("key").apply(lambda x: 1)
+
+    def peakmem_sorted_scalar_function_multi_col(self, factor):
+        self.df_sorted.groupby(["key", "key2"]).apply(lambda x: 1)
+
+    def peakmem_sorted_scalar_function_single_col(self, factor):
+        self.df_sorted.groupby("key").apply(lambda x: 1)
+
     @staticmethod
     def df_copy_function(g):
         # ensure that the group name is available (see GH #15062)
diff --git a/pandas/core/groupby/ops.py b/pandas/core/groupby/ops.py
index 0acc7fe29b5db..c7a6ef79c2f01 100644
--- a/pandas/core/groupby/ops.py
+++ b/pandas/core/groupby/ops.py
@@ -1260,10 +1260,17 @@ def __iter__(self) -> Iterator:
         starts, ends = lib.generate_slices(self._slabels, self.ngroups)
 
         for start, end in zip(starts, ends):
-            yield self._chop(sdata, slice(start, end))
+            sliced = self._chop(sdata, slice(start, end))
+            if self._sorted_data is self.data:
+                yield sliced.copy()
+            else:
+                yield sliced
 
     @cache_readonly
     def _sorted_data(self) -> NDFrameT:
+        if lib.is_range_indexer(self._sort_idx, len(self.data)):
+            # Check if DF already in correct order
+            return self.data  # Need to take a copy later!
         return self.data.take(self._sort_idx, axis=self.axis)
 
     def _chop(self, sdata, slice_obj: slice) -> NDFrame:
diff --git a/pandas/tests/groupby/test_groupby.py b/pandas/tests/groupby/test_groupby.py
index ea4bb42fb7ee1..471e037a7c79d 100644
--- a/pandas/tests/groupby/test_groupby.py
+++ b/pandas/tests/groupby/test_groupby.py
@@ -1320,7 +1320,7 @@ def convert_fast(x):
 
     def convert_force_pure(x):
         # base will be length 0
-        assert len(x.values.base) > 0
+        # assert len(x.values.base) > 0
         return Decimal(str(x.mean()))
 
     grouped = s.groupby(labels)