diff --git a/llama_stack/apis/scoring/scoring.py b/llama_stack/apis/scoring/scoring.py
index ec50ecab1..de3881e89 100644
--- a/llama_stack/apis/scoring/scoring.py
+++ b/llama_stack/apis/scoring/scoring.py
@@ -14,6 +14,7 @@ from llama_stack.apis.scoring_functions import *  # noqa: F403
 
 
 ScoringResult = Dict[str, Any]
+SingleScoringResult = Dict[str, Any]
 
 
 @json_schema_type
diff --git a/llama_stack/providers/impls/meta_reference/scoring/scorer/__init__.py b/llama_stack/providers/impls/meta_reference/scoring/scorer/__init__.py
new file mode 100644
index 000000000..756f351d8
--- /dev/null
+++ b/llama_stack/providers/impls/meta_reference/scoring/scorer/__init__.py
@@ -0,0 +1,5 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
diff --git a/llama_stack/providers/impls/meta_reference/scoring/scorer/base_scorer.py b/llama_stack/providers/impls/meta_reference/scoring/scorer/base_scorer.py
new file mode 100644
index 000000000..5f35f2ddd
--- /dev/null
+++ b/llama_stack/providers/impls/meta_reference/scoring/scorer/base_scorer.py
@@ -0,0 +1,35 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+from abc import ABC, abstractmethod
+from typing import Any, Dict, List
+from llama_stack.apis.scoring_functions import *  # noqa: F401, F403
+from llama_stack.apis.scoring import *  # noqa: F401, F403
+
+
+class BaseScorer(ABC):
+    """
+    Base interface class for all meta-reference scorers.
+    Each scorer needs to implement the following methods:
+    - score_row(self, row)
+    - aggregate(self, scorer_results)
+    """
+
+    def __init__(self, *args, **kwargs) -> None:
+        super().__init__(*args, **kwargs)
+
+    def __str__(self) -> str:
+        return self.__class__.__name__
+
+    @abstractmethod
+    def score_row(self, input_row: Dict[str, Any]) -> ScoringResult:
+        raise NotImplementedError()
+
+    @abstractmethod
+    def aggregate(self, scoring_results: List[ScoringResult]) -> ScoringResult:
+        raise NotImplementedError()
+
+    def score(self, input_rows: List[Dict[str, Any]]) -> List[ScoringResult]:
+        return [self.score_row(input_row) for input_row in input_rows]
diff --git a/llama_stack/providers/impls/meta_reference/scoring/scorer/equality_scorer.py b/llama_stack/providers/impls/meta_reference/scoring/scorer/equality_scorer.py
new file mode 100644
index 000000000..82ece9ebf
--- /dev/null
+++ b/llama_stack/providers/impls/meta_reference/scoring/scorer/equality_scorer.py
@@ -0,0 +1,24 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from llama_stack.providers.impls.meta_reference.scoring.scorer.base_scorer import (
+    BaseScorer,
+)
+
+
+class EqualityScorer(BaseScorer):
+    """
+    A scorer that assigns a score of 1.0 if the input string matches the target string, and 0.0 otherwise.
+    """
+
+    def __init__(self, target: str) -> None:
+        """
+        Initialize the EqualityScorer with a target string.
+
+        Args:
+            target (str): The target string to match against.
+        """
+        self.target = target
diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring.py b/llama_stack/providers/impls/meta_reference/scoring/scoring.py
index 71283d97c..895d74c53 100644
--- a/llama_stack/providers/impls/meta_reference/scoring/scoring.py
+++ b/llama_stack/providers/impls/meta_reference/scoring/scoring.py
@@ -41,7 +41,9 @@ class MetaReferenceScoringImpl(Scoring, ScoringFunctionsProtocolPrivate):
         ]
 
     async def register_scoring_function(self, function_def: ScoringFunctionDef) -> None:
-        pass
+        raise NotImplementedError(
+            "Dynamically registering scoring functions is not supported"
+        )
 
     async def score_batch(
         self, dataset_id: str, scoring_functions: List[str]
@@ -51,4 +53,7 @@ class MetaReferenceScoringImpl(Scoring, ScoringFunctionsProtocolPrivate):
     async def score(
         self, input_rows: List[Dict[str, Any]], scoring_functions: List[str]
     ) -> ScoreResponse:
-        print("!!!!score")
+        print(
+            f"scoring input_rows {input_rows} on scoring_functions {scoring_functions}"
+        )
+        return ScoreResponse()