diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index b93f6a380..2c5827d37 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -40,6 +40,7 @@
         }
     ],
     "paths": {
+<<<<<<< HEAD
         "/v1/eval/tasks/{task_id}/evaluations": {
             "post": {
                 "responses": {
@@ -234,6 +235,8 @@
                 "deprecated": true
             }
         },
+=======
+>>>>>>> 974941be (deprecation in OpenAPI spec)
         "/v1/eval-tasks": {
             "get": {
                 "responses": {
@@ -242,18 +245,27 @@
                         "content": {
                             "application/json": {
                                 "schema": {
+<<<<<<< HEAD
                                     "$ref": "#/components/schemas/ListBenchmarksResponse"
+=======
+                                    "$ref": "#/components/schemas/ListEvalTasksResponse"
+>>>>>>> 974941be (deprecation in OpenAPI spec)
                                 }
                             }
                         }
                     }
                 },
                 "tags": [
+<<<<<<< HEAD
                     "Benchmarks"
+=======
+                    "EvalTasks"
+>>>>>>> 974941be (deprecation in OpenAPI spec)
                 ],
                 "description": "",
                 "parameters": [],
                 "deprecated": true
+<<<<<<< HEAD
             },
             "post": {
                 "responses": {
@@ -318,6 +330,8 @@
                     "required": true
                 },
                 "deprecated": true
+=======
+>>>>>>> 974941be (deprecation in OpenAPI spec)
             }
         },
         "/v1/datasetio/rows": {
@@ -2645,7 +2659,89 @@
     "jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
     "components": {
         "schemas": {
+<<<<<<< HEAD
             "AgentCandidate": {
+=======
+            "EvalTask": {
+                "type": "object",
+                "properties": {
+                    "identifier": {
+                        "type": "string"
+                    },
+                    "provider_resource_id": {
+                        "type": "string"
+                    },
+                    "provider_id": {
+                        "type": "string"
+                    },
+                    "type": {
+                        "type": "string",
+                        "const": "eval_task",
+                        "default": "eval_task"
+                    },
+                    "dataset_id": {
+                        "type": "string"
+                    },
+                    "scoring_functions": {
+                        "type": "array",
+                        "items": {
+                            "type": "string"
+                        }
+                    },
+                    "metadata": {
+                        "type": "object",
+                        "additionalProperties": {
+                            "oneOf": [
+                                {
+                                    "type": "null"
+                                },
+                                {
+                                    "type": "boolean"
+                                },
+                                {
+                                    "type": "number"
+                                },
+                                {
+                                    "type": "string"
+                                },
+                                {
+                                    "type": "array"
+                                },
+                                {
+                                    "type": "object"
+                                }
+                            ]
+                        }
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "identifier",
+                    "provider_resource_id",
+                    "provider_id",
+                    "type",
+                    "dataset_id",
+                    "scoring_functions",
+                    "metadata"
+                ]
+            },
+            "ListEvalTasksResponse": {
+                "type": "object",
+                "properties": {
+                    "data": {
+                        "type": "array",
+                        "items": {
+                            "$ref": "#/components/schemas/EvalTask"
+                        }
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "data"
+                ]
+            },
+            "AppendRowsRequest": {
+>>>>>>> 974941be (deprecation in OpenAPI spec)
                 "type": "object",
                 "properties": {
                     "type": {
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index b30025020..c743ce47a 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -10,6 +10,7 @@ info:
 servers:
   - url: http://any-hosted-llama-stack.com
 paths:
+<<<<<<< HEAD
   /v1/eval/tasks/{task_id}/evaluations:
     post:
       responses:
@@ -125,6 +126,8 @@ paths:
           schema:
             type: string
       deprecated: true
+=======
+>>>>>>> 974941be (deprecation in OpenAPI spec)
   /v1/eval-tasks:
     get:
       responses:
@@ -133,6 +136,7 @@ paths:
           content:
             application/json:
               schema:
+<<<<<<< HEAD
                 $ref: '#/components/schemas/ListBenchmarksResponse'
       tags:
         - Benchmarks
@@ -179,6 +183,14 @@ paths:
               $ref: '#/components/schemas/DeprecatedRunEvalRequest'
         required: true
       deprecated: true
+=======
+                $ref: '#/components/schemas/ListEvalTasksResponse'
+      tags:
+        - EvalTasks
+      description: ''
+      parameters: []
+      deprecated: true
+>>>>>>> 974941be (deprecation in OpenAPI spec)
   /v1/datasetio/rows:
     get:
       responses:
@@ -1598,7 +1610,59 @@ jsonSchemaDialect: >-
   https://json-schema.org/draft/2020-12/schema
 components:
   schemas:
+<<<<<<< HEAD
     AgentCandidate:
+=======
+    EvalTask:
+      type: object
+      properties:
+        identifier:
+          type: string
+        provider_resource_id:
+          type: string
+        provider_id:
+          type: string
+        type:
+          type: string
+          const: eval_task
+          default: eval_task
+        dataset_id:
+          type: string
+        scoring_functions:
+          type: array
+          items:
+            type: string
+        metadata:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+      additionalProperties: false
+      required:
+        - identifier
+        - provider_resource_id
+        - provider_id
+        - type
+        - dataset_id
+        - scoring_functions
+        - metadata
+    ListEvalTasksResponse:
+      type: object
+      properties:
+        data:
+          type: array
+          items:
+            $ref: '#/components/schemas/EvalTask'
+      additionalProperties: false
+      required:
+        - data
+    AppendRowsRequest:
+>>>>>>> 974941be (deprecation in OpenAPI spec)
       type: object
       properties:
         type:
diff --git a/docs/openapi_generator/pyopenapi/generator.py b/docs/openapi_generator/pyopenapi/generator.py
index e37c45690..0f3b99784 100644
--- a/docs/openapi_generator/pyopenapi/generator.py
+++ b/docs/openapi_generator/pyopenapi/generator.py
@@ -647,6 +647,7 @@ class Generator:
         description = "\n".join(
             filter(None, [doc_string.short_description, doc_string.long_description])
         )
+
         return Operation(
             tags=[op.defining_class.__name__],
             summary=None,
diff --git a/llama_stack/apis/eval_tasks/eval_tasks.py b/llama_stack/apis/eval_tasks/eval_tasks.py
new file mode 100644
index 000000000..9a26fd0c0
--- /dev/null
+++ b/llama_stack/apis/eval_tasks/eval_tasks.py
@@ -0,0 +1,71 @@
+# 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 typing import Any, Dict, List, Literal, Optional, Protocol, runtime_checkable
+
+from llama_models.schema_utils import json_schema_type, webmethod
+from pydantic import BaseModel, Field
+
+from llama_stack.apis.resource import Resource, ResourceType
+
+
+class CommonEvalTaskFields(BaseModel):
+    dataset_id: str
+    scoring_functions: List[str]
+    metadata: Dict[str, Any] = Field(
+        default_factory=dict,
+        description="Metadata for this evaluation task",
+    )
+
+
+@json_schema_type
+class EvalTask(CommonEvalTaskFields, Resource):
+    type: Literal[ResourceType.eval_task.value] = ResourceType.eval_task.value
+
+    @property
+    def task_id(self) -> str:
+        return self.identifier
+
+    @property
+    def provider_eval_task_id(self) -> str:
+        return self.provider_resource_id
+
+
+class EvalTaskInput(CommonEvalTaskFields, BaseModel):
+    task_id: str
+    provider_id: Optional[str] = None
+    provider_eval_task_id: Optional[str] = None
+
+
+class ListEvalTasksResponse(BaseModel):
+    data: List[EvalTask]
+
+
+@runtime_checkable
+class EvalTasks(Protocol):
+    @webmethod(route="/eval-tasks", method="GET")
+    async def DEPRECATED_list_eval_tasks_deprecated(
+        self,
+    ) -> ListEvalTasksResponse: ...
+
+    @webmethod(route="/eval/tasks", method="GET")
+    async def list_eval_tasks(self) -> ListEvalTasksResponse: ...
+
+    @webmethod(route="/eval/tasks/{task_id}", method="GET")
+    async def get_eval_task(
+        self,
+        task_id: str,
+    ) -> Optional[EvalTask]: ...
+
+    @webmethod(route="/eval/tasks", method="POST")
+    async def register_eval_task(
+        self,
+        task_id: str,
+        dataset_id: str,
+        scoring_functions: List[str],
+        provider_eval_task_id: Optional[str] = None,
+        provider_id: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> None: ...