[BUG] Benchmark registration order affects reported outcomes

#include <benchmark/benchmark.h>
#include <gtest/gtest.h>

/**
 * defines / pre-allocates a std::vector<std::wstring> examples (within g_dataset)
 */
#include "Helpers.h"

#include <chrono>
#include <cstdint>
#include <ranges>
#include <vector>
#include <execution>
#include <codecvt>

std::string DoWork(const std::wstring& input)
{
    std::string result(input.size(), '\0');
    std::transform(std::execution::par_unseq, std::begin(input), std::end(input), std::begin(result),
                   [](wchar_t inChar) { return (char)(inChar & 0x0ff); });
    return result;
}

std::wstring DoWork1(const std::string& input)
{
    std::wstring result(input.size(), L'\0');
    std::transform(std::execution::par_unseq, std::begin(input), std::end(input), std::begin(result),
                   [](wchar_t inChar) { return (wchar_t)(inChar & 0x0ff); });
    return result;
}

template <typename InStringT,
    typename Fn,
    typename OutStringT = std::invoke_result_t<Fn,InStringT>>
void RunOnExamples(const std::vector<InStringT>& examples, Fn&& fn,
                  std::vector<OutStringT>& results)
{
    for (size_t iterations = 0; iterations < examples.size(); iterations++) {
        results[iterations] = fn(examples[iterations]);
    }
}

static void BM_DoWork(benchmark::State& state)
{
    state.PauseTiming();

    auto expectedResults = std::vector<std::string>(g_dataset.examples.size());

    state.ResumeTiming();

    while (state.KeepRunningBatch(g_dataset.examples.size())) {
        RunOnExamples(g_dataset.examples, DoWork, expectedResults);
    }

    state.SetItemsProcessed(state.iterations() * g_dataset.examples.size());
}

static void BM_DoWork1(benchmark::State& state)
{
    state.PauseTiming();

    auto expectedResults = std::vector<std::wstring>(g_dataset.examples.size());

    std::vector<std::string> examples(g_dataset.examples.size());
    static std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> myconv;
    for (size_t i = 0; i < g_dataset.examples.size(); i++) {
        examples[i] = myconv.to_bytes(g_dataset.examples[i]);
    }

    state.ResumeTiming();

    while (state.KeepRunningBatch(g_dataset.examples.size())) {
        RunOnExamples(examples, DoWork1, expectedResults);
    }

    state.SetItemsProcessed(state.iterations() * g_dataset.examples.size());
}

#pragma endregion

#pragma region Run benchmarks

BENCHMARK(BM_DoWork);
BENCHMARK(BM_DoWork);
BENCHMARK(BM_DoWork);
BENCHMARK(BM_DoWork1);
BENCHMARK(BM_DoWork1);
BENCHMARK(BM_DoWork1);

#pragma endregion

Run on (20 X 2918 MHz CPU s)
CPU Caches:
  L1 Data 48 KiB (x10)
  L1 Instruction 32 KiB (x10)
  L2 Unified 1280 KiB (x10)
  L3 Unified 24576 KiB (x1)
------------------------------------------------------------------------------
Benchmark                    Time             CPU   Iterations UserCounters...
------------------------------------------------------------------------------
BM_DoWork                   86347685 ns         6438 ns      1000000 items_per_second=155.34G/s
BM_DoWork                   86352813 ns        10688 ns      1000000 items_per_second=93.5673G/s
BM_DoWork                   86358084 ns        15141 ns      1000000 items_per_second=66.0475G/s
BM_DoWork1                  86363182 ns        19484 ns      1000000 items_per_second=51.3232G/s
BM_DoWork1                  86369707 ns        25062 ns      1000000 items_per_second=39.9002G/s
BM_DoWork1                  86378334 ns        32438 ns      1000000 items_per_second=30.8285G/s