diff --git a/evaluations/evaluations/evaluators/number_match.py b/evaluations/evaluations/evaluators/number_match.py
index 8ea70304..eb657e24 100644
--- a/evaluations/evaluations/evaluators/number_match.py
+++ b/evaluations/evaluations/evaluators/number_match.py
@@ -33,13 +33,14 @@ class NumberMatchEvaluator(Evaluator):
         gold = extract_numbers(str(ctx.expected_output))
         if not gold:
             return 0.0
-        # Gold mixes conventions: signs for changes are inconsistent (+0.2 vs
-        # -1.9) and ratios appear as either a percent (37.81) or a decimal
-        # (0.3781). Compare the declared answer by magnitude, at a ×100 scale
-        # either way. Safe because we score only the single ANSWER-line number.
+        # Gold mixes conventions: change signs are inconsistent (+0.2 vs -1.9),
+        # ratios appear as a percent or a decimal (37.81 vs 0.3781), and figures
+        # appear in units or thousands (4575515 vs 4575515000). Compare the
+        # declared answer by magnitude at ×100 and ×1000 scales either way. Safe
+        # because we score only the single ANSWER-line number.
         target = abs(gold[0])
         candidates = [abs(c) for c in extract_numbers(_answer_segment(str(ctx.output)))]
-        scales = (1.0, 0.01, 100.0)
+        scales = (1.0, 0.01, 100.0, 0.001, 1000.0)
         matched = any(
             numbers_close(c * s, target, self.eps) for c in candidates for s in scales
         )
diff --git a/evaluations/tests/test_evaluators.py b/evaluations/tests/test_evaluators.py
index b70a74b3..c0adecd3 100644
--- a/evaluations/tests/test_evaluators.py
+++ b/evaluations/tests/test_evaluators.py
@@ -116,6 +116,17 @@ class TestNumberMatchEvaluator:
         ctx = self._make_ctx("30.443", "ANSWER: 2330.8%")
         assert self.evaluator.evaluate(ctx) == 0.0
 
+    def test_thousands_convention(self) -> None:
+        # gold is in thousands; model gives the full-dollar figure
+        ctx = self._make_ctx("4575515.0", "...\nANSWER: 4575515000")
+        assert self.evaluator.evaluate(ctx) == 1.0
+
+    def test_thousands_convention_reversed(self) -> None:
+        ctx = self._make_ctx(
+            "46.30434782608695", "fair value per share\nANSWER: 46304.35"
+        )
+        assert self.evaluator.evaluate(ctx) == 1.0
+
     def test_answer_line_ignores_reasoning_distractors(self) -> None:
         # gold matches a distractor in the body, but the declared answer is wrong
         ctx = self._make_ctx(