diff --git a/reasoning_gym/algorithmic/letter_jumble.py b/reasoning_gym/algorithmic/letter_jumble.py
index f92d8f2b..728c9c67 100644
--- a/reasoning_gym/algorithmic/letter_jumble.py
+++ b/reasoning_gym/algorithmic/letter_jumble.py
@@ -3,7 +3,7 @@
 import re
 from dataclasses import dataclass
 from random import Random
-from typing import Optional
+from typing import Dict, Optional
 
 from reasoning_gym.data import read_data_file
 
@@ -99,5 +99,27 @@ class LetterJumbleDataset(ProceduralDataset):
             },
         }
 
+    def score_answer(self, answer: Optional[str], entry: Dict[str, any]) -> float:
+        """Determine if the solution provided solves this task.
+
+        The function awards 1.0 for a correct answer.
+
+        Args:
+            answer (Optional[str]): The user's answer.
+            entry (Dict[str, any]): The original dataset entry containing the correct answer.
+
+        Returns:
+            float: The computed score between 0.0 and 1.0.
+        """
+
+        if answer == None:
+            return 0.0
+
+        s_answer = answer.strip().lower()
+        if not s_answer == entry["answer"].strip().lower():
+            return 0.01
+        else:
+            return 1.0
+
 
 register_dataset("letter_jumble", LetterJumbleDataset, LetterJumbleConfig)
diff --git a/tests/test_letter_jumble.py b/tests/test_letter_jumble.py
index 8203f2f0..89f860b5 100644
--- a/tests/test_letter_jumble.py
+++ b/tests/test_letter_jumble.py
@@ -108,6 +108,11 @@ def test_letter_jumble_dataset_items():
             assert config.min_word_len <= len(word) <= config.max_word_len
             assert word.isalpha()
 
+        # Test the scoring
+        assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
+        assert dataset.score_answer(answer="gibberish", entry=item) == 0.01
+        assert dataset.score_answer(answer=None, entry=item) == 0.0
+
 
 def test_letter_jumble_iteration():
     """Test that iteration respects dataset size"""