diff --git a/src/lighteval/metrics/normalizations.py b/src/lighteval/metrics/normalizations.py
index ef55681b1..0dad8d3a9 100644
--- a/src/lighteval/metrics/normalizations.py
+++ b/src/lighteval/metrics/normalizations.py
@@ -68,7 +68,9 @@ def lower(text: str) -> str:
     def _tokenize(text):
         return re.split(" |-", text)
 
-    tokens = [white_space_fix(remove_articles(homogeneize_numbers(remove_punc(lower(t))))) for t in _tokenize(text)]
+    # homogeneize_numbers must run before remove_punc: otherwise remove_punc strips the decimal
+    # point first, so "1.0" -> "10" -> float -> "10.0" (distinct numbers collide, and 1.0 != 1).
+    tokens = [white_space_fix(remove_articles(remove_punc(homogeneize_numbers(lower(t))))) for t in _tokenize(text)]
     return " ".join([t for t in tokens if t != ""]).strip()
 
 
diff --git a/tests/test_unit_base_metrics.py b/tests/test_unit_base_metrics.py
index 575ebf595..51fb58d68 100644
--- a/tests/test_unit_base_metrics.py
+++ b/tests/test_unit_base_metrics.py
@@ -95,6 +95,15 @@ def test_quasi_exact_match(self):
         res = em.compute_one_item("", "")
         assert res == 0
 
+    def test_quasi_exact_match_numbers(self):
+        em = ExactMatches(normalize_gold=helm_normalizer, normalize_pred=helm_normalizer)
+
+        # Numbers that are equal but formatted differently must match (homogeneize_numbers' goal).
+        assert em.compute_one_item("1.0", "1") == 1
+        # Distinct numbers must NOT be scored as an exact match.
+        assert em.compute_one_item("10", "1.0") == 0
+        assert em.compute_one_item("3.14", "314") == 0
+
     def test_prefix_exact_match(self):
         em = ExactMatches(
             strip_strings=True,