diff --git a/evalharness/data/datasets/bbh.py b/evalharness/data/datasets/bbh.py
index 5d3e09f..b86dfcd 100644
--- a/evalharness/data/datasets/bbh.py
+++ b/evalharness/data/datasets/bbh.py
@@ -28,7 +28,8 @@ def bbh_few_shot(split: str, subset: str, n: int):
         task_type='qa',
         tags=['reasoning'],
         description='BIG-Bench Hard, 27 subtasks (each subset caches under bbh/<hash>).',
-        few_shot_split='official_cot',  # -> bbh_few_shot hook (3-shot official CoT)
+        few_shot_split='official_cot',  # -> bbh_few_shot hook (official CoT)
+        few_shot_num=3,               # paper/es default: 3-shot
     )
 )
 def bbh():