diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index 381f37f1f..cba7829a1 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -81,7 +81,7 @@
                 "deprecated": true
             }
         },
-        "/v1/eval-tasks/{benchmark_id}": {
+        "/v1/eval-tasks/{task_id}": {
             "get": {
                 "responses": {
                     "200": {
@@ -109,7 +109,7 @@
                 "parameters": [
                     {
                         "name": "task_id",
-                        "in": "query",
+                        "in": "path",
                         "required": true,
                         "schema": {
                             "type": "string"
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index 83bc5483c..0bc498776 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -35,7 +35,7 @@ paths:
               $ref: '#/components/schemas/DeprecatedEvaluateRowsRequest'
         required: true
       deprecated: true
-  /v1/eval-tasks/{benchmark_id}:
+  /v1/eval-tasks/{task_id}:
     get:
       responses:
         '200':
@@ -51,7 +51,7 @@ paths:
       description: ''
       parameters:
         - name: task_id
-          in: query
+          in: path
           required: true
           schema:
             type: string
diff --git a/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb b/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
index 857b7f133..8eecf84ab 100644
--- a/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
+++ b/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
@@ -1017,14 +1017,14 @@
         "    \"content\": SYSTEM_PROMPT_TEMPLATE.format(subject=subset),\n",
         "}\n",
         "\n",
-        "client.benchmarks.register(\n",
-        "    benchmark_id=\"meta-reference::mmmu\",\n",
+        "client.eval_tasks.register(\n",
+        "    eval_task_id=\"meta-reference::mmmu\",\n",
         "    dataset_id=f\"mmmu-{subset}-{split}\",\n",
         "    scoring_functions=[\"basic::regex_parser_multiple_choice_answer\"],\n",
         ")\n",
         "\n",
         "response = client.eval.evaluate_rows(\n",
-        "    benchmark_id=\"meta-reference::mmmu\",\n",
+        "    task_id=\"meta-reference::mmmu\",\n",
         "    input_rows=eval_rows,\n",
         "    scoring_functions=[\"basic::regex_parser_multiple_choice_answer\"],\n",
         "    task_config={\n",
@@ -1196,8 +1196,8 @@
         "    provider_id=\"together\",\n",
         ")\n",
         "\n",
-        "client.benchmarks.register(\n",
-        "    benchmark_id=\"meta-reference::simpleqa\",\n",
+        "client.eval_tasks.register(\n",
+        "    eval_task_id=\"meta-reference::simpleqa\",\n",
         "    dataset_id=simpleqa_dataset_id,\n",
         "    scoring_functions=[\"llm-as-judge::405b-simpleqa\"],\n",
         ")\n",
@@ -1214,7 +1214,7 @@
         "            \"sampling_params\": {\n",
         "                \"strategy\": {\n",
         "                    \"type\": \"greedy\",\n",
-        "                },b\n",
+        "                },\n",
         "                \"max_tokens\": 4096,\n",
         "                \"repeat_penalty\": 1.0,\n",
         "            },\n",
@@ -1352,7 +1352,7 @@
         "}\n",
         "\n",
         "response = client.eval.evaluate_rows(\n",
-        "    benchmark_id=\"meta-reference::simpleqa\",\n",
+        "    task_id=\"meta-reference::simpleqa\",\n",
         "    input_rows=eval_rows.rows,\n",
         "    scoring_functions=[\"llm-as-judge::405b-simpleqa\"],\n",
         "    task_config={\n",