diff --git a/cpp/src/arrow/compute/kernels/aggregate-benchmark.cc b/cpp/src/arrow/compute/kernels/aggregate-benchmark.cc
index bbc923f6ebd83..085843e700d14 100644
--- a/cpp/src/arrow/compute/kernels/aggregate-benchmark.cc
+++ b/cpp/src/arrow/compute/kernels/aggregate-benchmark.cc
@@ -18,22 +18,16 @@
 #include "benchmark/benchmark.h"
 
 #include <vector>
-#ifdef _MSC_VER
-#include <intrin.h>
-#else
-#include <immintrin.h>
-#endif
 
 #include "arrow/builder.h"
-#include "arrow/memory_pool.h"
-#include "arrow/testing/gtest_util.h"
-#include "arrow/testing/random.h"
-#include "arrow/util/bit-util.h"
-
 #include "arrow/compute/benchmark-util.h"
 #include "arrow/compute/context.h"
 #include "arrow/compute/kernel.h"
 #include "arrow/compute/kernels/sum.h"
+#include "arrow/memory_pool.h"
+#include "arrow/testing/gtest_util.h"
+#include "arrow/testing/random.h"
+#include "arrow/util/bit-util.h"
 
 namespace arrow {
 namespace compute {
diff --git a/dev/archery/archery/cli.py b/dev/archery/archery/cli.py
index b7b077ab87c7e..0178d58a03f68 100644
--- a/dev/archery/archery/cli.py
+++ b/dev/archery/archery/cli.py
@@ -352,9 +352,12 @@ def benchmark_diff(ctx, src, preserve, suite_filter, benchmark_filter,
 
         regressions = 0
         runner_comp = RunnerComparator(runner_cont, runner_base, threshold)
+
+        # TODO(kszucs): test that the output is properly formatted jsonlines
         for comparator in runner_comp.comparisons:
             regressions += comparator.regression
             json.dump(comparator, output, cls=JsonEncoder)
+            output.write('\n')
 
         sys.exit(regressions)