diff --git a/.github/workflows/vllm_ascend_test_nightly_a3.yaml b/.github/workflows/vllm_ascend_test_nightly_a3.yaml
index 6e2b149d..dff9bc9c 100644
--- a/.github/workflows/vllm_ascend_test_nightly_a3.yaml
+++ b/.github/workflows/vllm_ascend_test_nightly_a3.yaml
@@ -53,7 +53,7 @@ jobs:
             config_file_path: DeepSeek-V3.yaml
             size: 2
           - name: multi-node-qwen3-dp
-            config_file_path: Qwen3-235B-A3B.yaml
+            config_file_path: Qwen3-235B-A22B.yaml
             size: 2
           - name: multi-node-dpsk-4node-pd
             config_file_path: DeepSeek-R1-W8A8.yaml
diff --git a/docs/source/developer_guide/contribution/multi_node_test.md b/docs/source/developer_guide/contribution/multi_node_test.md
index c5d1ecbc..20d90ce2 100644
--- a/docs/source/developer_guide/contribution/multi_node_test.md
+++ b/docs/source/developer_guide/contribution/multi_node_test.md
@@ -142,7 +142,7 @@ currently, the multi-node test workflow defined in the [vllm_ascend_test_nightly
                 config_file_path: tests/e2e/nightly/multi_node/config/models/DeepSeek-V3.yaml
                 size: 2
             - name: multi-node-qwen3-dp
-                config_file_path: tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A3B.yaml
+                config_file_path: tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A22B.yaml
                 size: 2
             - name: multi-node-dpsk-4node-pd
                 config_file_path: tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8.yaml
diff --git a/tests/e2e/models/configs/Qwen3-8B-Base.yaml b/tests/e2e/models/configs/Qwen3-8B-Base.yaml
deleted file mode 100644
index 73026446..00000000
--- a/tests/e2e/models/configs/Qwen3-8B-Base.yaml
+++ /dev/null
@@ -1,14 +0,0 @@
-model_name: "Qwen/Qwen3-8B-Base"
-hardware: "Atlas A2 Series"
-tasks:
-- name: "gsm8k"
-  metrics:
-  - name: "exact_match,strict-match"
-    value: 0.82
-  - name: "exact_match,flexible-extract"
-    value: 0.83
-- name: "ceval-valid"
-  metrics:
-  - name: "acc,none"
-    value: 0.82
-num_fewshot: 5
diff --git a/tests/e2e/models/configs/accuracy.txt b/tests/e2e/models/configs/accuracy.txt
index b5f7aeed..d4238488 100644
--- a/tests/e2e/models/configs/accuracy.txt
+++ b/tests/e2e/models/configs/accuracy.txt
@@ -12,6 +12,6 @@ InternVL3-8B.yaml
 InternVL3_5-8B.yaml
 ERNIE-4.5-21B-A3B-PT.yaml
 gemma-3-4b-it.yaml
-internlm-7b.yaml
+internlm3-8b-instruct.yaml
 Molmo-7B-D-0924.yaml
 llava-1.5-7b-hf.yaml
diff --git a/tests/e2e/models/configs/internlm-7b.yaml b/tests/e2e/models/configs/internlm3-8b-instruct.yaml
similarity index 80%
rename from tests/e2e/models/configs/internlm-7b.yaml
rename to tests/e2e/models/configs/internlm3-8b-instruct.yaml
index ceccc53d..490ae42b 100644
--- a/tests/e2e/models/configs/internlm-7b.yaml
+++ b/tests/e2e/models/configs/internlm3-8b-instruct.yaml
@@ -1,4 +1,4 @@
-model_name: "Shanghai_AI_Laboratory/internlm-7b"
+model_name: "Shanghai_AI_Laboratory/internlm3-8b-instruct"
 hardware: "Atlas A2 Series"
 tasks:
 - name: "ceval-valid"
diff --git a/tests/e2e/models/conftest.py b/tests/e2e/models/conftest.py
index a75659f4..9370ff8c 100644
--- a/tests/e2e/models/conftest.py
+++ b/tests/e2e/models/conftest.py
@@ -21,7 +21,7 @@ def pytest_addoption(parser):
     parser.addoption(
         "--config",
         action="store",
-        default="./tests/e2e/models/configs/Qwen3-8B-Base.yaml",
+        default="./tests/e2e/models/configs/Qwen3-8B.yaml",
         help="Path to the model config YAML file",
     )
     parser.addoption(
diff --git a/tests/e2e/nightly/models/test_deepseek_r1_w8a8_eplb.py b/tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8_eplb.py
similarity index 98%
rename from tests/e2e/nightly/models/test_deepseek_r1_w8a8_eplb.py
rename to tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8_eplb.py
index 498eadfe..a49a83a9 100644
--- a/tests/e2e/nightly/models/test_deepseek_r1_w8a8_eplb.py
+++ b/tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8_eplb.py
@@ -25,7 +25,7 @@ from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases
 
 MODELS = [
-    "vllm-ascend/DeepSeek-R1-W8A8",
+    "vllm-ascend/DeepSeek-R1-0528-W8A8",
 ]
 
 prompts = [
diff --git a/tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A3B.yaml b/tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A22B.yaml
similarity index 84%
rename from tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A3B.yaml
rename to tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A22B.yaml
index dd3c7db7..40ae591e 100644
--- a/tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A3B.yaml
+++ b/tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A22B.yaml
@@ -48,6 +48,17 @@ deployment:
         --no-enable-prefix-caching
         --gpu-memory-utilization 0.9
 benchmarks:
+  perf:
+    case_type: performance
+    dataset_path: vllm-ascend/GSM8K-in3500-bs2800
+    request_conf: vllm_api_stream_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+    num_prompts: 2800
+    max_out_len: 1500
+    batch_size: 700
+    request_rate: 11.2
+    baseline: 1
+    threshold: 0.97
   acc:
     case_type: accuracy
     dataset_path: vllm-ascend/gsm8k