Why old rand() faster than uniform_real_distribution in openMP?

Can someone explain to me why second for loop, with old rand(), executes a lot faster than the first loop? I have seen through multiple post here that using c++11 engine and uniform distribution are being recommended bacause rand() + multithreading is a perf bottleneck? Also as suggested I have generator and function per thread.

int main(int argc, char *argv[])
{

    std::vector<mt19937> generators(omp_get_max_threads());
    std::vector<uniform_real_distribution<double>> functions(omp_get_max_threads());
    
    for (int i = 0; i < omp_get_max_threads(); i++)
    {
        // seed is random
        generators[i] =  mt19937(1654 + 17*i);
        functions[i] =   uniform_real_distribution<double>(0.0,1.0);
    }

    double itime = omp_get_wtime();
    #pragma omp parallel for        
        for (int i =0; i < 10000000; i++)
        {
            int a = functions[omp_get_thread_num()](generators[omp_get_thread_num()]);
        }
        
    
    double end = omp_get_wtime() - itime;
    
    srand(time(NULL));
    double start = omp_get_wtime();
        #pragma omp parallel for
        for (int i =0; i < 10000000; i++)
        {
            int a = ((double) rand() / (RAND_MAX));
        }
    double endR  = omp_get_wtime() - start;

    cout << "Generator: " << end<<endl;
    cout<<"Old: "<<endR << endl;
}