diff --git a/evals/benchmark/stresscli/locust/aistress.py b/evals/benchmark/stresscli/locust/aistress.py
index 1264ac41..436713e0 100644
--- a/evals/benchmark/stresscli/locust/aistress.py
+++ b/evals/benchmark/stresscli/locust/aistress.py
@@ -120,12 +120,16 @@ def bench_main(self):
             "faqgenfixed",
             "faqgenbench",
         ]
+        if self.environment.parsed_options.bench_target in ["faqgenfixed", "faqgenbench"]:
+            req_params = {"data": reqData}
+        else:
+            req_params = {"json": reqData}
         test_start_time = time.time()
         try:
             start_ts = time.perf_counter()
             with self.client.post(
                 url,
-                json=reqData,
+                **req_params,
                 stream=True if self.environment.parsed_options.bench_target in streaming_bench_target else False,
                 catch_response=True,
                 timeout=self.environment.parsed_options.http_timeout,
@@ -169,6 +173,22 @@ def bench_main(self):
                                         complete_response += content
                                 except json.JSONDecodeError:
                                     continue
+                        elif self.environment.parsed_options.bench_target in ["faqgenfixed", "faqgenbench"]:
+                            client = sseclient.SSEClient(resp)
+                            for event in client.events():
+                                if first_token_ts is None:
+                                    first_token_ts = time.perf_counter()
+                                try:
+                                    data = json.loads(event.data)
+                                    for op in data["ops"]:
+                                        if op["path"] == "/logs/HuggingFaceEndpoint/final_output":
+                                            generations = op["value"].get("generations", [])
+                                            for generation in generations:
+                                                for item in generation:
+                                                    text = item.get("text", "")
+                                                    complete_response += text
+                                except json.JSONDecodeError:
+                                    continue
                         else:
                             client = sseclient.SSEClient(resp)
                             for event in client.events():
diff --git a/evals/benchmark/stresscli/locust/faqgenfixed.py b/evals/benchmark/stresscli/locust/faqgenfixed.py
index b648a567..75f3d29b 100644
--- a/evals/benchmark/stresscli/locust/faqgenfixed.py
+++ b/evals/benchmark/stresscli/locust/faqgenfixed.py
@@ -9,12 +9,11 @@ def getUrl():
 
 
 def getReqData():
-    # return {
-    #     "inputs": "What is the revenue of Nike in last 10 years before 2023? Give me detail",
-    #     "parameters": {"max_new_tokens": 128, "do_sample": True},
-    # }
-    # return {"query": "What is the revenue of Nike in last 10 years before 2023? Give me detail", "max_tokens": 128}
-    return {"messages": "What is the revenue of Nike in last 10 years before 2023? Give me detail", "max_tokens": 128}
+    return {
+        "messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E6.",
+        "max_tokens": 128,
+        "top_k": 1,
+    }
 
 
 def respStatics(environment, reqData, respData):
diff --git a/evals/benchmark/stresscli/locust/tokenresponse.py b/evals/benchmark/stresscli/locust/tokenresponse.py
index 4b6bfe75..afa487ef 100644
--- a/evals/benchmark/stresscli/locust/tokenresponse.py
+++ b/evals/benchmark/stresscli/locust/tokenresponse.py
@@ -15,7 +15,7 @@ def testFunc():
 
 def respStatics(environment, req, resp):
     tokenizer = transformers.AutoTokenizer.from_pretrained(environment.parsed_options.llm_model)
-    if environment.parsed_options.bench_target in ["chatqnafixed", "chatqnabench"]:
+    if environment.parsed_options.bench_target in ["chatqnafixed", "chatqnabench", "faqgenfixed", "faqgenbench"]:
         num_token_input_prompt = len(tokenizer.encode(req["messages"]))
     elif environment.parsed_options.bench_target in ["llmfixed"]:
         num_token_input_prompt = len(tokenizer.encode(req["query"]))