diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index 057abb5fa..b35c325a8 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -6812,7 +6812,10 @@
                         "enum": [
                             "post-training/messages",
                             "eval/question-answer",
-                            "eval/messages-answer"
+                            "eval/messages-answer",
+                            "scoring/question-generation-answer",
+                            "scoring/messages-generation-answer",
+                            "scoring/generation-answer"
                         ],
                         "title": "DatasetPurpose",
                         "description": "Purpose of the dataset. Each purpose has a required input data schema."
@@ -8792,7 +8795,11 @@
                             "type": "string",
                             "enum": [
                                 "post-training/messages",
-                                "eval/messages-answer"
+                                "eval/question-answer",
+                                "eval/messages-answer",
+                                "scoring/question-generation-answer",
+                                "scoring/messages-generation-answer",
+                                "scoring/generation-answer"
                             ],
                             "title": "DatasetPurpose",
                             "description": "Purpose of the dataset. Each purpose has a required input data schema."
@@ -9887,9 +9894,12 @@
                         "enum": [
                             "post-training/messages",
                             "eval/question-answer",
-                            "eval/messages-answer"
+                            "eval/messages-answer",
+                            "scoring/question-generation-answer",
+                            "scoring/messages-generation-answer",
+                            "scoring/generation-answer"
                         ],
-                        "description": "The purpose of the dataset. One of - \"post-training/messages\": The dataset contains a messages column with list of messages for post-training. { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, world!\"}, {\"role\": \"assistant\", \"content\": \"Hello, world!\"}, ] } - \"eval/question-answer\": The dataset contains a question column and an answer column for evaluation. { \"question\": \"What is the capital of France?\", \"answer\": \"Paris\" } - \"eval/messages-answer\": The dataset contains a messages column with list of messages and an answer column for evaluation. { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, my name is John Doe.\"}, {\"role\": \"assistant\", \"content\": \"Hello, John Doe. How can I help you today?\"}, {\"role\": \"user\", \"content\": \"What's my name?\"}, ], \"answer\": \"John Doe\" }"
+                        "description": "The purpose of the dataset. One of - \"post-training/messages\": The dataset contains a messages column with list of messages for post-training. { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, world!\"}, {\"role\": \"assistant\", \"content\": \"Hello, world!\"}, ] } - \"eval/question-answer\": The dataset contains a question column and an answer column for evaluation. { \"question\": \"What is the capital of France?\", \"answer\": \"Paris\" } - \"eval/messages-answer\": The dataset contains a messages column with list of messages and an answer column for evaluation. { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, my name is John Doe.\"}, {\"role\": \"assistant\", \"content\": \"Hello, John Doe. How can I help you today?\"}, {\"role\": \"user\", \"content\": \"What's my name?\"}, ], \"answer\": \"John Doe\" } - \"scoring/question-generation-answer\": The dataset contains a question column, a generation column and an answer column for scoring. { \"question\": \"What is the capital of France?\", \"generation\": \"Paris\", \"answer\": \"Paris\" } - \"scoring/messages-generation-answer\": The dataset contains a messages column with list of messages, a generation column and an answer column for scoring. { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, my name is John Doe.\"}, {\"role\": \"assistant\", \"content\": \"Hello, John Doe. How can I help you today?\"}, {\"role\": \"user\", \"content\": \"What's my name?\"}, ], \"generation\": \"John Doe\", \"answer\": \"John Doe\" } - \"scoring/generation-answer\": The dataset contains a generation column and an answer column for scoring. { \"generation\": \"Paris\", \"answer\": \"Paris\" }"
                     },
                     "source": {
                         "$ref": "#/components/schemas/DataSource",
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index a06cdcc95..54d548e57 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -4718,6 +4718,9 @@ components:
             - post-training/messages
             - eval/question-answer
             - eval/messages-answer
+            - scoring/question-generation-answer
+            - scoring/messages-generation-answer
+            - scoring/generation-answer
           title: DatasetPurpose
           description: >-
             Purpose of the dataset. Each purpose has a required input data schema.
@@ -6070,7 +6073,11 @@ components:
             type: string
             enum:
               - post-training/messages
+              - eval/question-answer
               - eval/messages-answer
+              - scoring/question-generation-answer
+              - scoring/messages-generation-answer
+              - scoring/generation-answer
             title: DatasetPurpose
             description: >-
               Purpose of the dataset. Each purpose has a required input data schema.
@@ -6779,6 +6786,9 @@ components:
             - post-training/messages
             - eval/question-answer
             - eval/messages-answer
+            - scoring/question-generation-answer
+            - scoring/messages-generation-answer
+            - scoring/generation-answer
           description: >-
             The purpose of the dataset. One of - "post-training/messages": The dataset
             contains a messages column with list of messages for post-training. {
@@ -6790,7 +6800,18 @@ components:
             column for evaluation. { "messages": [ {"role": "user", "content": "Hello,
             my name is John Doe."}, {"role": "assistant", "content": "Hello, John
             Doe. How can I help you today?"}, {"role": "user", "content": "What's
-            my name?"}, ], "answer": "John Doe" }
+            my name?"}, ], "answer": "John Doe" } - "scoring/question-generation-answer":
+            The dataset contains a question column, a generation column and an answer
+            column for scoring. { "question": "What is the capital of France?", "generation":
+            "Paris", "answer": "Paris" } - "scoring/messages-generation-answer": The
+            dataset contains a messages column with list of messages, a generation
+            column and an answer column for scoring. { "messages": [ {"role": "user",
+            "content": "Hello, my name is John Doe."}, {"role": "assistant", "content":
+            "Hello, John Doe. How can I help you today?"}, {"role": "user", "content":
+            "What's my name?"}, ], "generation": "John Doe", "answer": "John Doe"
+            } - "scoring/generation-answer": The dataset contains a generation column
+            and an answer column for scoring. { "generation": "Paris", "answer": "Paris"
+            }
         source:
           $ref: '#/components/schemas/DataSource'
           description: >-
diff --git a/llama_stack/apis/datasets/datasets.py b/llama_stack/apis/datasets/datasets.py
index e1285ef9a..812b373f9 100644
--- a/llama_stack/apis/datasets/datasets.py
+++ b/llama_stack/apis/datasets/datasets.py
@@ -38,11 +38,37 @@ class DatasetPurpose(Enum):
             ],
             "answer": "John Doe"
         }
+    :cvar scoring/question-generation-answer: The dataset contains a question column, a generation column and an answer column.
+        {
+            "question": "What is the capital of France?",
+            "generation": "Paris",
+            "answer": "Paris"
+        }
+    :cvar scoring/messages-generation-answer: The dataset contains a messages column with list of messages, a generation column and an answer column.
+        {
+            "messages": [
+                {"role": "user", "content": "Hello, my name is John Doe."},
+                {"role": "assistant", "content": "Hello, John Doe. How can I help you today?"},
+                {"role": "user", "content": "What's my name?"},
+            ],
+            "generation": "John Doe",
+            "answer": "John Doe"
+        }
+    :cvar scoring/generation-answer: The dataset contains a generation column and an answer column.
+        {
+            "generation": "Paris",
+            "answer": "Paris"
+        }
     """
     post_training_messages = "post-training/messages"
+
     eval_question_answer = "eval/question-answer"
     eval_messages_answer = "eval/messages-answer"
 
+    scoring_question_generation_answer = "scoring/question-generation-answer"
+    scoring_messages_generation_answer = "scoring/messages-generation-answer"
+    scoring_generation_answer = "scoring/generation-answer"
+
     # TODO: add more schemas here
 
 
@@ -180,6 +206,27 @@ class Datasets(Protocol):
                     ],
                     "answer": "John Doe"
                 }
+            - "scoring/question-generation-answer": The dataset contains a question column, a generation column and an answer column for scoring.
+                {
+                    "question": "What is the capital of France?",
+                    "generation": "Paris",
+                    "answer": "Paris"
+                }
+            - "scoring/messages-generation-answer": The dataset contains a messages column with list of messages, a generation column and an answer column for scoring.
+                {
+                    "messages": [
+                        {"role": "user", "content": "Hello, my name is John Doe."},
+                        {"role": "assistant", "content": "Hello, John Doe. How can I help you today?"},
+                        {"role": "user", "content": "What's my name?"},
+                    ],
+                    "generation": "John Doe",
+                    "answer": "John Doe"
+                }
+            - "scoring/generation-answer": The dataset contains a generation column and an answer column for scoring.
+                {
+                    "generation": "Paris",
+                    "answer": "Paris"
+                }
         :param source: The data source of the dataset. Examples:
            - {
                "type": "uri",