diff --git a/asv_bench/benchmarks/groupby.py b/asv_bench/benchmarks/groupby.py
index 490c2ccbd4c..8124883b6a0 100644
--- a/asv_bench/benchmarks/groupby.py
+++ b/asv_bench/benchmarks/groupby.py
@@ -34,17 +34,17 @@ def time_agg_large_num_groups(self, method, ndim):
         ds = getattr(self, f"ds{ndim}d")
         getattr(ds.groupby("b"), method)()
 
-    def time_groupby_binary_op_1d(self):
-        self.ds1d - self.ds1d_mean
+    def time_binary_op_1d(self):
+        self.ds1d.groupby("b") - self.ds1d_mean
 
-    def time_groupby_binary_op_2d(self):
-        self.ds2d - self.ds2d_mean
+    def time_binary_op_2d(self):
+        self.ds2d.groupby("b") - self.ds2d_mean
 
-    def peakmem_groupby_binary_op_1d(self):
-        self.ds1d - self.ds1d_mean
+    def peakmem_binary_op_1d(self):
+        self.ds1d.groupby("b") - self.ds1d_mean
 
-    def peakmem_groupby_binary_op_2d(self):
-        self.ds2d - self.ds2d_mean
+    def peakmem_binary_op_2d(self):
+        self.ds2d.groupby("b") - self.ds2d_mean
 
 
 class GroupByDask(GroupBy):
@@ -71,10 +71,10 @@ def setup(self, *args, **kwargs):
         self.ds1d = self.ds1d.to_dataframe()
         self.ds1d_mean = self.ds1d.groupby("b").mean()
 
-    def time_groupby_binary_op_2d(self):
+    def time_binary_op_2d(self):
         raise NotImplementedError
 
-    def peakmem_groupby_binary_op_2d(self):
+    def peakmem_binary_op_2d(self):
         raise NotImplementedError
 
 
@@ -90,10 +90,10 @@ def setup(self, *args, **kwargs):
         self.ds1d = self.ds1d.chunk({"dim_0": 50}).to_dataframe()
         self.ds1d_mean = self.ds1d.groupby("b").mean()
 
-    def time_groupby_binary_op_2d(self):
+    def time_binary_op_2d(self):
         raise NotImplementedError
 
-    def peakmem_groupby_binary_op_2d(self):
+    def peakmem_binary_op_2d(self):
         raise NotImplementedError
 
 
@@ -123,18 +123,6 @@ def time_agg_large_num_groups(self, method, ndim):
         ds = getattr(self, f"ds{ndim}d")
         getattr(ds.resample(time="48H"), method)()
 
-    def time_groupby_binary_op_1d(self):
-        self.ds1d - self.ds1d_mean
-
-    def time_groupby_binary_op_2d(self):
-        self.ds2d - self.ds2d_mean
-
-    def peakmem_groupby_binary_op_1d(self):
-        self.ds1d - self.ds1d_mean
-
-    def peakmem_groupby_binary_op_2d(self):
-        self.ds2d - self.ds2d_mean
-
 
 class ResampleDask(Resample):
     def setup(self, *args, **kwargs):