diff --git a/fuzzer.py b/fuzzer.py
index 5888e8a..fb99e38 100644
--- a/fuzzer.py
+++ b/fuzzer.py
@@ -166,10 +166,18 @@ def get_test_case_source(f_name: str, test_case: Params, i: int, indent: int):
 {space}{single_indent}assert {call_statement(f_name_orig, test_case)} == {repr(output)}"""
 
 
-def get_test_class(f_name: str, cases: set[Params]) -> str:
-    f_name_orig = BranchTransformer.to_original_name(f_name)
+def get_test_import_stmt(names: list[str]):
+    imports = ["from unittest import TestCase"]
 
-    test_class = (f"from unittest import TestCase\n\nfrom {module_of[f_name]} import {f_name_orig}\n\n\n"
-                  f"class Test_{f_name_orig}(TestCase):\n")
-    test_class += "\n\n".join([get_test_case_source(f_name, case, i + 1, 1) for i, case in enumerate(cases)])
-    return test_class
+    for orig_f_name in names:
+        f_name = BranchTransformer.to_instrumented_name(orig_f_name)
+        imports.append(f"from {'.'.join(module_of[f_name])} import {orig_f_name}")
+
+    return "\n".join(imports) + "\n"
+
+
+def get_test_class(orig_f_name: str, cases: set[Params]) -> str:
+    f_name = BranchTransformer.to_instrumented_name(orig_f_name)
+    return (f"class Test_{orig_f_name}(TestCase):\n" +
+            "\n\n".join([get_test_case_source(f_name, case, i + 1, 1) for i, case in enumerate(cases)]) +
+            "\n")
diff --git a/genetic.py b/genetic.py
index 886edc1..d2d2799 100644
--- a/genetic.py
+++ b/genetic.py
@@ -1,7 +1,6 @@
 import argparse
 import os
 import random
-import sys
 from functools import partial
 
 import frozendict
@@ -56,8 +55,8 @@ def init_deap():
     creator.create("Individual", list, fitness=creator.Fitness)
 
 
-def generate(f_name: str):
-    orig_name = instrument.BranchTransformer.to_original_name(f_name)
+def generate(orig_name: str) -> set[instrument.Params]:
+    f_name = instrument.BranchTransformer.to_instrumented_name(orig_name)
     args = instrument.functions[f_name]
 
     range_start, range_end = instrument.n_of_branches[f_name]
@@ -106,6 +105,9 @@ def generate(f_name: str):
             top_result = archive.build_suite()
             top_coverage = cov
 
+            if tot_covered == total_branches:
+                break
+
     return top_result
 
 
@@ -150,11 +152,13 @@ def compute_fitness(f_name: str, archive: Archive, individual: list) -> tuple[fl
     return fitness,
 
 
-def build_suite(f_name: str):
-    instr_name = instrument.BranchTransformer.to_instrumented_name(f_name)
-    cases = generate(instr_name)
-    with open(os.path.join(OUT_DIR, "test_" + f_name + ".py"), "w") as f:
-        f.write(get_test_class(instr_name, cases))
+def build_suite(filename: str, f_names: list[str]):
+    suite = [(name, generate(name)) for name in f_names]
+
+    with open(os.path.join(OUT_DIR, f"test_{filename}.py"), "w") as f:
+        f.write(fuzzer.get_test_import_stmt(f_names))
+        f.write("\n\n")
+        f.write("\n\n".join([get_test_class(name, cases) for name, cases in suite]))
 
 
 def main():
@@ -169,9 +173,8 @@ def main():
     instrument.load_benchmark(save_instrumented=False, files=parser.parse_args().file)
     init_deap()
 
-    for instr_f in tqdm.tqdm(sorted(instrument.functions.keys()), desc="Generating tests"):
-        print("", file=sys.stderr)
-        build_suite(instrument.BranchTransformer.to_original_name(instr_f))
+    for file_name, functions in tqdm.tqdm(instrument.get_benchmark().items(), desc="Generating tests"):
+        build_suite(file_name, functions)
 
 
 if __name__ == '__main__':
diff --git a/instrument.py b/instrument.py
index d62fad5..0b31d46 100644
--- a/instrument.py
+++ b/instrument.py
@@ -1,11 +1,13 @@
 import ast
 import os.path
 import sys
+from collections import defaultdict
 from typing import Optional
 
 import astunparse
 import tqdm
 from frozendict import frozendict
+
 from operators import evaluate_condition
 
 ROOT_DIR: str = os.path.dirname(__file__)
@@ -85,7 +87,7 @@ SignatureDict = dict[str, list[Arg]]
 
 n_of_branches: dict[str, tuple[int, int]] = {}
 functions: SignatureDict = {}
-module_of: dict[str, str] = {}
+module_of: dict[str, list[str]] = {}
 
 
 def instrument(source_path: str, target_path: str, save_instrumented=True):
@@ -130,9 +132,7 @@ def instrument(source_path: str, target_path: str, save_instrumented=True):
             arg_types.append((arg.arg, arg_type))
 
         functions[f.name] = arg_types
-        module_of[f.name] = os.path.normpath(os.path.relpath(source_path, ROOT_DIR)) \
-            .replace(".py", "") \
-            .replace("/", ".")
+        module_of[f.name] = os.path.splitext(os.path.normpath(os.path.relpath(source_path, ROOT_DIR)))[0].split("/")
 
 
 def invoke(f_name: str, f_args: Params) -> any:
@@ -176,5 +176,19 @@ def call_statement(f_name: str, f_args: Params) -> str:
     return f"{f_name}({', '.join(arg_list)})"
 
 
+def get_benchmark() -> dict[str, list[str]]:
+    """
+    Returns a dictionary associated each source code file name loaded (without extension) with the list of
+    (non-instrumented) function names defined within it
+    """
+
+    names: defaultdict[str, list[str]] = defaultdict(list)
+
+    for f in functions:
+        names[module_of[f][-1]].append(BranchTransformer.to_original_name(f))
+
+    return dict(names)
+
+
 if __name__ == '__main__':
     load_benchmark(save_instrumented=True)
diff --git a/muttest.py b/muttest.py
new file mode 100644
index 0000000..95ac21f
--- /dev/null
+++ b/muttest.py
@@ -0,0 +1,41 @@
+import argparse
+import os
+import re
+import sys
+
+import instrument
+
+ROOT_DIR = os.path.dirname(__file__)
+IN_SOURCE_DIR = os.path.join(ROOT_DIR, "benchmark")
+IN_TEST_DIR = os.path.join(ROOT_DIR, "tests")
+OUT_DIR = os.path.join(ROOT_DIR, "tests")
+
+
+def run_mutpy(test_path: str, source_path: str):
+    stream = os.popen(f'mut.py --target \'{source_path}\' --unit-test \'{test_path}\'')
+    output = stream.read()
+    score = re.search('Mutation score \[.*\]: (\d+\.\d+)\%', output).group(1)
+    print(output, file=sys.stderr)
+    print(f"Score is: {score}")
+
+
+def main():
+    parser = argparse.ArgumentParser(prog='muttest.py',
+                                     description='Runs MutPy over generated test suite.')
+    parser.add_argument('file', type=str, help="Source file to test",
+                        nargs="*")
+
+    files = parser.parse_args().file
+    if len(files) == 0:
+        to_test = instrument.get_benchmark().keys()
+    else:
+        to_test = [os.path.splitext(os.path.basename(file))[0] for file in files]
+
+    for filename in to_test:
+        source_path = os.path.join(IN_SOURCE_DIR, f"{filename}.py")
+        test_path = os.path.join(IN_TEST_DIR, f"test_{filename}.py")
+        run_mutpy(test_path, source_path)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/requirements.txt b/requirements.txt
index b01f1ce..c184cdd 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -2,4 +2,5 @@ nltk==3.8.1
 deap==1.4.1
 astunparse==1.6.3
 frozendict==2.3.8
-tqdm==4.66.1
\ No newline at end of file
+tqdm==4.66.1
+MutPy==0.6.1
\ No newline at end of file
diff --git a/tests/test_anagram_check.py b/tests/test_anagram_check.py
index f3cc27b..e1d4108 100644
--- a/tests/test_anagram_check.py
+++ b/tests/test_anagram_check.py
@@ -1,20 +1,16 @@
 from unittest import TestCase
-
 from benchmark.anagram_check import anagram_check
 
 
 class Test_anagram_check(TestCase):
     def test_anagram_check_1(self):
-        assert anagram_check(s1='B', s2='o8') == False
+        assert anagram_check(s1='@', s2='{') == False
 
     def test_anagram_check_2(self):
-        assert anagram_check(s1=' ', s2='u') == False
+        assert anagram_check(s1='', s2='X~|') == False
 
     def test_anagram_check_3(self):
-        assert anagram_check(s1='', s2='') == True
+        assert anagram_check(s1='?kv|d', s2='43J!j') == False
 
     def test_anagram_check_4(self):
-        assert anagram_check(s1='?8H', s2='') == False
-
-    def test_anagram_check_5(self):
-        assert anagram_check(s1='@m', s2='Pj') == False
\ No newline at end of file
+        assert anagram_check(s1='U', s2='') == False
diff --git a/tests/test_caesar_cipher.py b/tests/test_caesar_cipher.py
new file mode 100644
index 0000000..6387ba4
--- /dev/null
+++ b/tests/test_caesar_cipher.py
@@ -0,0 +1,19 @@
+from unittest import TestCase
+from benchmark.caesar_cipher import encrypt
+from benchmark.caesar_cipher import decrypt
+
+
+class Test_encrypt(TestCase):
+    def test_encrypt_1(self):
+        assert encrypt(strng='(B{6M K', key=90) == '#=v1HzF'
+
+    def test_encrypt_2(self):
+        assert encrypt(strng='t3Cv', key=84) == 'i(8k'
+
+
+class Test_decrypt(TestCase):
+    def test_decrypt_1(self):
+        assert decrypt(strng='4.J<IH{', key=11) == ')#?1>=p'
+
+    def test_decrypt_2(self):
+        assert decrypt(strng='5v8K', key=32) == 'tVw+'
diff --git a/tests/test_cd_count.py b/tests/test_cd_count.py
deleted file mode 100644
index 81b863e..0000000
--- a/tests/test_cd_count.py
+++ /dev/null
@@ -1,23 +0,0 @@
-from unittest import TestCase
-
-from benchmark.common_divisor_count import cd_count
-
-
-class Test_cd_count(TestCase):
-    def test_cd_count_1(self):
-        assert cd_count(a=-946, b=0) == 2
-
-    def test_cd_count_2(self):
-        assert cd_count(a=873, b=164) == 1
-
-    def test_cd_count_3(self):
-        assert cd_count(a=0, b=-90) == 2
-
-    def test_cd_count_4(self):
-        assert cd_count(a=783, b=-749) == 1
-
-    def test_cd_count_5(self):
-        assert cd_count(a=621, b=-23) == 2
-
-    def test_cd_count_6(self):
-        assert cd_count(a=-635, b=444) == 1
\ No newline at end of file
diff --git a/tests/test_check_armstrong.py b/tests/test_check_armstrong.py
index cc42a7a..b1953b0 100644
--- a/tests/test_check_armstrong.py
+++ b/tests/test_check_armstrong.py
@@ -1,20 +1,16 @@
 from unittest import TestCase
-
 from benchmark.check_armstrong import check_armstrong
 
 
 class Test_check_armstrong(TestCase):
     def test_check_armstrong_1(self):
-        assert check_armstrong(n=370) == True
+        assert check_armstrong(n=220) == False
 
     def test_check_armstrong_2(self):
-        assert check_armstrong(n=5) == False
-
-    def test_check_armstrong_3(self):
-        assert check_armstrong(n=1) == True
-
-    def test_check_armstrong_4(self):
         assert check_armstrong(n=0) == True
 
-    def test_check_armstrong_5(self):
-        assert check_armstrong(n=346) == False
\ No newline at end of file
+    def test_check_armstrong_3(self):
+        assert check_armstrong(n=35) == False
+
+    def test_check_armstrong_4(self):
+        assert check_armstrong(n=1) == True
diff --git a/tests/test_common_divisor_count.py b/tests/test_common_divisor_count.py
new file mode 100644
index 0000000..61aa9dc
--- /dev/null
+++ b/tests/test_common_divisor_count.py
@@ -0,0 +1,19 @@
+from unittest import TestCase
+from benchmark.common_divisor_count import cd_count
+
+
+class Test_cd_count(TestCase):
+    def test_cd_count_1(self):
+        assert cd_count(a=-741, b=-457) == 2
+
+    def test_cd_count_2(self):
+        assert cd_count(a=111, b=99) == 6
+
+    def test_cd_count_3(self):
+        assert cd_count(a=740, b=-169) == 3
+
+    def test_cd_count_4(self):
+        assert cd_count(a=0, b=449) == 2
+
+    def test_cd_count_5(self):
+        assert cd_count(a=910, b=0) == 2
diff --git a/tests/test_decrypt.py b/tests/test_decrypt.py
deleted file mode 100644
index 33135e6..0000000
--- a/tests/test_decrypt.py
+++ /dev/null
@@ -1,8 +0,0 @@
-from unittest import TestCase
-
-from benchmark.caesar_cipher import decrypt
-
-
-class Test_decrypt(TestCase):
-    def test_decrypt_1(self):
-        assert decrypt(strng='\\nEGQ&', key=41) == '3E{}(ý'
\ No newline at end of file
diff --git a/tests/test_encrypt.py b/tests/test_encrypt.py
deleted file mode 100644
index 3d0bfb2..0000000
--- a/tests/test_encrypt.py
+++ /dev/null
@@ -1,11 +0,0 @@
-from unittest import TestCase
-
-from benchmark.caesar_cipher import encrypt
-
-
-class Test_encrypt(TestCase):
-    def test_encrypt_1(self):
-        assert encrypt(strng='ToU}[G4}', key=70) == ';V<dB.zd'
-
-    def test_encrypt_2(self):
-        assert encrypt(strng='Ja%b7$x?S', key=91) == 'F]!^3 t;O'
\ No newline at end of file
diff --git a/tests/test_exponentiation.py b/tests/test_exponentiation.py
index d1a5f78..4430f5a 100644
--- a/tests/test_exponentiation.py
+++ b/tests/test_exponentiation.py
@@ -1,8 +1,7 @@
 from unittest import TestCase
-
 from benchmark.exponentiation import exponentiation
 
 
 class Test_exponentiation(TestCase):
     def test_exponentiation_1(self):
-        assert exponentiation(baseNumber=-963, power=53) == -135579247021508037271506970896774862890401757444424074712158036994660498207857413507120369768136011010001454548485109484383268428282840962739680900835831388403
\ No newline at end of file
+        assert exponentiation(baseNumber=771, power=474) == 2909210833489491293378842744086198556807698873805727913089141407566444307615874153703385291756938871584773318376082715282560979576003239005635105383696346203211241092618871232636438256963156478107480938401494345016352663544251711600300410294173581492138819773752393733341176714058194552308171277586141676868377612692878963273168698528314579277083563280084863520035365678210031287889772088909455822915896837639257753201805916075921630683337539958393092565260283310668864760181646358235718551645281913578630788801289878777658471432050952913833670208688658984707550985045490960816912971550665977523223101342154277056798749106996358053949918115208536589659714855628074010414625147806448539987417123348274550207168187859690445981358534944856355827734611140152400206513027687952209274470811281719393462377048863468859856738711318208410712979094433620095183415992926567580010288921145076938532560376641152027545404240780516247328096495417952049358953162107534093353491634575118361354594270772437236185212631466579892318815456992018956388226428774320211702200525700236584879799246396547556437518901096156284575576838239123951159155896959994089575333138430692507022983208229342846303747301555381846496103057947746652402219370385064952595644297390849057715440768800731610673913446165042850598544860086460108426470227274128434108967174102649421640276420078514555815576331215899881
diff --git a/tests/test_gcd.py b/tests/test_gcd.py
index b0c5680..2f086ce 100644
--- a/tests/test_gcd.py
+++ b/tests/test_gcd.py
@@ -1,20 +1,19 @@
 from unittest import TestCase
-
 from benchmark.gcd import gcd
 
 
 class Test_gcd(TestCase):
     def test_gcd_1(self):
-        assert gcd(a=531, b=338) == 1
+        assert gcd(a=1, b=292) == 1
 
     def test_gcd_2(self):
-        assert gcd(a=1, b=395) == 1
+        assert gcd(a=706, b=706) == 706
 
     def test_gcd_3(self):
-        assert gcd(a=71, b=496) == 1
+        assert gcd(a=506, b=1) == 1
 
     def test_gcd_4(self):
-        assert gcd(a=644, b=644) == 644
+        assert gcd(a=695, b=765) == 765
 
     def test_gcd_5(self):
-        assert gcd(a=581, b=1) == 1
\ No newline at end of file
+        assert gcd(a=140, b=29) == 140
diff --git a/tests/test_longest_sorted_substr.py b/tests/test_longest_substring.py
similarity index 75%
rename from tests/test_longest_sorted_substr.py
rename to tests/test_longest_substring.py
index 8e90859..172cbdc 100644
--- a/tests/test_longest_sorted_substr.py
+++ b/tests/test_longest_substring.py
@@ -1,8 +1,7 @@
 from unittest import TestCase
-
 from benchmark.longest_substring import longest_sorted_substr
 
 
 class Test_longest_sorted_substr(TestCase):
     def test_longest_sorted_substr_1(self):
-        assert longest_sorted_substr(s='YW|jsXG,u') == 'W|'
\ No newline at end of file
+        assert longest_sorted_substr(s='sixBa') == 'ix'
diff --git a/tests/test_rabin_karp.py b/tests/test_rabin_karp.py
new file mode 100644
index 0000000..a877d68
--- /dev/null
+++ b/tests/test_rabin_karp.py
@@ -0,0 +1,16 @@
+from unittest import TestCase
+from benchmark.rabin_karp import rabin_karp_search
+
+
+class Test_rabin_karp_search(TestCase):
+    def test_rabin_karp_search_1(self):
+        assert rabin_karp_search(pat='3gx!', txt='~*J~%eC') == [0]
+
+    def test_rabin_karp_search_2(self):
+        assert rabin_karp_search(pat='`gO7Vq!kU', txt='=DLaH\\p~[') == []
+
+    def test_rabin_karp_search_3(self):
+        assert rabin_karp_search(pat='', txt='%gxypQ7L') == []
+
+    def test_rabin_karp_search_4(self):
+        assert rabin_karp_search(pat='@', txt='H@@|DPma"') == [1, 2]
diff --git a/tests/test_rabin_karp_search.py b/tests/test_rabin_karp_search.py
deleted file mode 100644
index 5bcb5c8..0000000
--- a/tests/test_rabin_karp_search.py
+++ /dev/null
@@ -1,20 +0,0 @@
-from unittest import TestCase
-
-from benchmark.rabin_karp import rabin_karp_search
-
-
-class Test_rabin_karp_search(TestCase):
-    def test_rabin_karp_search_1(self):
-        assert rabin_karp_search(pat='', txt='m 2') == []
-
-    def test_rabin_karp_search_2(self):
-        assert rabin_karp_search(pat='.w5', txt='55[Ax5X') == []
-
-    def test_rabin_karp_search_3(self):
-        assert rabin_karp_search(pat='h@=y', txt='JcEC') == []
-
-    def test_rabin_karp_search_4(self):
-        assert rabin_karp_search(pat='X', txt='J@X"') == [2]
-
-    def test_rabin_karp_search_5(self):
-        assert rabin_karp_search(pat='>0OPQ', txt='Dzxu8:(P') == []
\ No newline at end of file
diff --git a/tests/test_raildecrypt.py b/tests/test_raildecrypt.py
deleted file mode 100644
index aadc14e..0000000
--- a/tests/test_raildecrypt.py
+++ /dev/null
@@ -1,17 +0,0 @@
-from unittest import TestCase
-
-from benchmark.railfence_cipher import raildecrypt
-
-
-class Test_raildecrypt(TestCase):
-    def test_raildecrypt_1(self):
-        assert raildecrypt(st='q338K a{.', k=9) == 'q338K a{.'
-
-    def test_raildecrypt_2(self):
-        assert raildecrypt(st='q338K a{.', k=3) == 'q8{K3 .a3'
-
-    def test_raildecrypt_3(self):
-        assert raildecrypt(st='Hi=BC/', k=557) == 'Hi=BC/'
-
-    def test_raildecrypt_4(self):
-        assert raildecrypt(st='X61*8p', k=5) == 'X61*p8'
\ No newline at end of file
diff --git a/tests/test_railencrypt.py b/tests/test_railencrypt.py
deleted file mode 100644
index 010950c..0000000
--- a/tests/test_railencrypt.py
+++ /dev/null
@@ -1,14 +0,0 @@
-from unittest import TestCase
-
-from benchmark.railfence_cipher import railencrypt
-
-
-class Test_railencrypt(TestCase):
-    def test_railencrypt_1(self):
-        assert railencrypt(st=')x8ro;BVm', k=865) == ')x8ro;BVm'
-
-    def test_railencrypt_2(self):
-        assert railencrypt(st='q338K a{.', k=4) == 'qa3 {3K.8'
-
-    def test_railencrypt_3(self):
-        assert railencrypt(st='X61*8p', k=5) == 'X61*p8'
\ No newline at end of file
diff --git a/tests/test_railfence_cipher.py b/tests/test_railfence_cipher.py
new file mode 100644
index 0000000..3608808
--- /dev/null
+++ b/tests/test_railfence_cipher.py
@@ -0,0 +1,25 @@
+from unittest import TestCase
+from benchmark.railfence_cipher import railencrypt
+from benchmark.railfence_cipher import raildecrypt
+
+
+class Test_railencrypt(TestCase):
+    def test_railencrypt_1(self):
+        assert railencrypt(st='78l%K2', k=3) == '\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'
+
+    def test_railencrypt_2(self):
+        assert railencrypt(st='f', k=25) == '\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'
+
+    def test_railencrypt_3(self):
+        assert railencrypt(st='(la_UD^', k=2) == '\x00\x00\x00\x00\x00\x00\x00'
+
+
+class Test_raildecrypt(TestCase):
+    def test_raildecrypt_1(self):
+        assert raildecrypt(st='(la_UD^', k=2) == ''
+
+    def test_raildecrypt_2(self):
+        assert raildecrypt(st="ZZ.B/8M'M", k=3) == ''
+
+    def test_raildecrypt_3(self):
+        assert raildecrypt(st='9[HS4', k=960) == ''
diff --git a/tests/test_zeller.py b/tests/test_zeller.py
deleted file mode 100644
index 68cbc07..0000000
--- a/tests/test_zeller.py
+++ /dev/null
@@ -1,23 +0,0 @@
-from unittest import TestCase
-
-from benchmark.zellers_birthday import zeller
-
-
-class Test_zeller(TestCase):
-    def test_zeller_1(self):
-        assert zeller(d=-134, m=797, y=67) == 'Sunday'
-
-    def test_zeller_2(self):
-        assert zeller(d=-156, m=10, y=-57) == 'Wednesday'
-
-    def test_zeller_3(self):
-        assert zeller(d=715, m=444, y=74) == 'Thursday'
-
-    def test_zeller_4(self):
-        assert zeller(d=-726, m=864, y=-16) == 'Thursday'
-
-    def test_zeller_5(self):
-        assert zeller(d=31, m=910, y=2) == 'Sunday'
-
-    def test_zeller_6(self):
-        assert zeller(d=369, m=-917, y=-1000) == 'Sunday'
\ No newline at end of file
diff --git a/tests/test_zellers_birthday.py b/tests/test_zellers_birthday.py
new file mode 100644
index 0000000..50fd286
--- /dev/null
+++ b/tests/test_zellers_birthday.py
@@ -0,0 +1,16 @@
+from unittest import TestCase
+from benchmark.zellers_birthday import zeller
+
+
+class Test_zeller(TestCase):
+    def test_zeller_1(self):
+        assert zeller(d=-466, m=3, y=76) == 'Tuesday'
+
+    def test_zeller_2(self):
+        assert zeller(d=626, m=-928, y=27) == 'Saturday'
+
+    def test_zeller_3(self):
+        assert zeller(d=19, m=108, y=68) == 'Friday'
+
+    def test_zeller_4(self):
+        assert zeller(d=284, m=255, y=-6) == 'Thursday'