diff --git a/src/olmo_eval/common/scorers/ifeval.py b/src/olmo_eval/common/scorers/ifeval.py
index 16dad3bdb..ff708dcf6 100644
--- a/src/olmo_eval/common/scorers/ifeval.py
+++ b/src/olmo_eval/common/scorers/ifeval.py
@@ -1,7 +1,7 @@
 """Scorer for IFBench / IFEval instruction-following evaluation.
 
 Uses the ``ifbench`` package registry, which covers the original IFEval
-(DEFAULT) verifiers, the OOD verifiers used by ``allenai/IFBench_test2``,
+(DEFAULT) verifiers, the OOD verifiers used by ``allenai/IFBench_test``,
 and the verifiers used by the multi-turn ``VGraf/ifeval_mt`` slices. The
 scorer evaluates a response against per-instance instructions (looked up
 in ``instance.metadata["instruction_id_list"]`` / ``"kwargs"``) and writes
diff --git a/src/olmo_eval/evals/tasks/ifeval_ood.py b/src/olmo_eval/evals/tasks/ifeval_ood.py
index d3c65991c..11b583aa0 100644
--- a/src/olmo_eval/evals/tasks/ifeval_ood.py
+++ b/src/olmo_eval/evals/tasks/ifeval_ood.py
@@ -1,6 +1,6 @@
 """IFEval OOD: out-of-distribution instruction-following slice of IFBench.
 
-Dataset: ``allenai/IFBench_test2`` (300 prompts), each carrying a list of
+Dataset: ``allenai/IFBench_test`` (300 prompts), each carrying a list of
 instruction IDs and per-instruction kwargs. Verifiers come from the vendored
 registry in :mod:`olmo_eval.common.scorers.ifeval_deps`.
 
@@ -35,7 +35,7 @@
 
 @register("ifeval_ood")
 class IFEvalOOD(Task):
-    data_source = DataSource(path="allenai/IFBench_test2", split="train")
+    data_source = DataSource(path="allenai/IFBench_test", split="train")
     split = Split.TRAIN
     metrics = (
         IFEvalPromptStrictAccuracy(),