diff --git a/.github/workflows/CI.yml b/.github/workflows/pytest.yml
similarity index 92%
rename from .github/workflows/CI.yml
rename to .github/workflows/pytest.yml
index f1fddc58..2340d9d5 100644
--- a/.github/workflows/CI.yml
+++ b/.github/workflows/pytest.yml
@@ -1,4 +1,4 @@
-name: CI
+name: pytest
 
 on:
   push:
@@ -30,6 +30,7 @@ jobs:
           pip install .
           pip install pytest
           pip install pytest-cov
+          pip install pytest-benchmark
 
       - name: Run tests
         run: pytest --cov=pyerrors -v
diff --git a/.gitignore b/.gitignore
index 18c31bfa..77feb98c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -2,6 +2,7 @@ __pycache__
 *.pyc
 .ipynb_*
 .coverage
+.benchmarks
 .cache
 examples/B1k2_pcac_plateau.p
 examples/Untitled.*
diff --git a/tests/benchmark_test.py b/tests/benchmark_test.py
new file mode 100644
index 00000000..707b3791
--- /dev/null
+++ b/tests/benchmark_test.py
@@ -0,0 +1,55 @@
+import numpy as np
+import pyerrors as pe
+import pytest
+import time
+
+np.random.seed(0)
+
+def test_bench_mul(benchmark):
+    length = 1000
+    my_obs = pe.Obs([np.random.rand(length)], ['t1'])
+
+    def mul(x, y):
+        return x * y
+
+    benchmark(mul, my_obs, my_obs)
+
+
+def test_bench_cmul(benchmark):
+    length = 1000
+    my_obs = pe.CObs(pe.Obs([np.random.rand(length)], ['t1']),
+                     pe.Obs([np.random.rand(length)], ['t1']))
+
+    def mul(x, y):
+        return x * y
+
+    benchmark(mul, my_obs, my_obs)
+
+
+def test_bench_matmul(benchmark):
+    dim = 4
+    my_list = []
+    length = 1000
+    for i in range(dim ** 2):
+        my_list.append(pe.Obs([np.random.rand(length)], ['t1']))
+    my_array = np.array(my_list).reshape((dim, dim))
+
+    benchmark(pe.linalg.matmul, my_array, my_array)
+
+
+def test_bench_cmatmul(benchmark):
+    dim = 4
+    my_list = []
+    length = 1000
+    for i in range(dim ** 2):
+        my_list.append(pe.CObs(pe.Obs([np.random.rand(length)], ['t1']),
+                               pe.Obs([np.random.rand(length)], ['t1'])))
+    my_array = np.array(my_list).reshape((dim, dim))
+
+    benchmark(pe.linalg.matmul, my_array, my_array)
+
+
+def test_bench_gamma_method(benchmark):
+    length = 1000
+    my_obs = pe.Obs([np.random.rand(length)], ['t1'])
+    benchmark(my_obs.gamma_method)
diff --git a/tests/test_correlators.py b/tests/correlators_test.py
similarity index 100%
rename from tests/test_correlators.py
rename to tests/correlators_test.py
diff --git a/tests/test_dirac.py b/tests/dirac_test.py
similarity index 100%
rename from tests/test_dirac.py
rename to tests/dirac_test.py
diff --git a/tests/test_fits.py b/tests/fits_test.py
similarity index 100%
rename from tests/test_fits.py
rename to tests/fits_test.py
diff --git a/tests/test_linalg.py b/tests/linalg_test.py
similarity index 100%
rename from tests/test_linalg.py
rename to tests/linalg_test.py
diff --git a/tests/test_pyerrors.py b/tests/pyerrors_test.py
similarity index 100%
rename from tests/test_pyerrors.py
rename to tests/pyerrors_test.py
diff --git a/tests/test_roots.py b/tests/roots_test.py
similarity index 100%
rename from tests/test_roots.py
rename to tests/roots_test.py