Trying to Understand how python multiprocessing and threading works together

Question

I am trying to understand how can I use threads inside the mutiple process, So that I could take full advatage of all my cores.

import multiprocessing
from time import sleep
import time
import queue

class Work:
    """
      Dummy class to represent some intensive work
    """
    def __init__(self,a,b):
        self.a=a
        self.b=b

    def do(self):
        sleep_time=5
        sleep(sleep_time)
        print("slept for {}".format(sleep_time))
        print("process name :{}".format(multiprocessing.current_process().name))
        print("Thread name :{}".format(threading.current_thread().name))
            return self.a+self.b



class ThreadWrapper(threading.Thread):
    def __init__(self,obj,method_name):
        super().__init__()
        self.obj=obj
        self.method_name=method_name
        self.result=None

    def run(self):
        try:
            self.result=getattr(self.obj,self.method_name)()
        except Exception as e:
            print("Exception occured {}".format(e))

    def get_result(self):
        return self.result


def main(work_items,result_queue,kls,method_name):
    threads=[]
    for item in work_items:
        obj=kls(*item)
        threads.append(ThreadWrapper(obj,method_name))
    for thread in threads:
        thread.start()
    for thread in threads:
        thread.join()
    for thread in threads:
        if not  thread.is_alive():
            result=thread.get_result()
            result_queue.put(result)



def threads_only():
    list_of_items=[(1,2),(3,4),(5,6),(1,2),(3,4),(5,6),(1,2),(3,4),(5,6)]
    result_queue=multiprocessing.Queue()
    main(list_of_items,result_queue,Work,'do')
    while not result_queue.empty():
        print(result_queue.get())

Case-1 ----> using both Multiprocessing and threading

if  __name__ == '__main__':
    t1=time.time()
    result_queue=multiprocessing.Queue()
    list_of_items=[[(1,2),(3,4),(5,6)],[(1,2),(3,4),(5,6)],[(1,2),(3,4),(5,6)]]
    processes = []
    for items in list_of_items :
        p = multiprocessing.Process(target=main,args=(items,result_queue,Work,'do')) # create a new Process
        processes.append(p)
    for process in processes:
        process.start()
        process.join()
    while not result_queue.empty():
        print(result_queue.get())   
    t2=time.time()
    print("Total time taken is {}".format(t2-t1))   #  Total time taken is 16.146932125091553

Case-2 Using only threading

if  __name__ == '__main__':
    t1=time.time()

    threads_only()

    t2=time.time()
    print("Total time taken is {}".format(t2-t1))   #  Total time taken is 5.06544041633606

Here is the summary:

Total_work_input=9

1.Without any concurrency Total_time_taken= 9*5s(sleep time)+ ~1s (actual work) =~ 46s

2.Case-1 (multiprocessing + threads) = 16.146932125091553s

3.Case-2 (Only Threads) = 5.06544041633606

I have 4 cores in my system,

os.cpu_count() 4

Shouldn't each process be given to each core ???

So that I should be getting similar result as Case-2 (~5 sec) where I have used only threading

What I am missing here?

Please help me understand