diff --git a/llama_stack/providers/datatypes.py b/llama_stack/providers/datatypes.py
index 84771190e..1194a5bd9 100644
--- a/llama_stack/providers/datatypes.py
+++ b/llama_stack/providers/datatypes.py
@@ -67,8 +67,6 @@ class ScoringFunctionsProtocolPrivate(Protocol):
 
 
 class EvalTasksProtocolPrivate(Protocol):
-    async def list_eval_tasks(self) -> List[EvalTask]: ...
-
     async def register_eval_task(self, eval_task: EvalTask) -> None: ...
 
 
diff --git a/llama_stack/providers/inline/eval/meta_reference/eval.py b/llama_stack/providers/inline/eval/meta_reference/eval.py
index 23d3cf6dc..f63d77421 100644
--- a/llama_stack/providers/inline/eval/meta_reference/eval.py
+++ b/llama_stack/providers/inline/eval/meta_reference/eval.py
@@ -56,9 +56,6 @@ class MetaReferenceEvalImpl(Eval, EvalTasksProtocolPrivate):
     async def register_eval_task(self, task_def: EvalTask) -> None:
         self.eval_tasks[task_def.identifier] = task_def
 
-    async def list_eval_tasks(self) -> List[EvalTask]:
-        return list(self.eval_tasks.values())
-
     async def validate_eval_input_dataset_schema(self, dataset_id: str) -> None:
         dataset_def = await self.datasets_api.get_dataset(dataset_identifier=dataset_id)
         if not dataset_def.dataset_schema or len(dataset_def.dataset_schema) == 0: