diff --git a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml
index 0d9f1452..08ebea9d 100644
--- a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml
+++ b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml
@@ -46,8 +46,8 @@ _benchmarks: &benchmarks
     max_out_len: 32768
     batch_size: 32
     top_k: 20
-    baseline: 96
-    threshold: 3
+    baseline: 100
+    threshold: 5
 
 # ==========================================
 # ACTUAL TEST CASES
diff --git a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
index cd47eef4..f2a8c995 100644
--- a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
+++ b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
@@ -41,5 +41,5 @@ test_cases:
         dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
         max_out_len: 32768
         batch_size: 32
-        baseline: 96
-        threshold: 3
+        baseline: 100
+        threshold: 5
diff --git a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
index 02b03bdd..b163685d 100644
--- a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
+++ b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
@@ -46,8 +46,8 @@ _benchmarks: &benchmarks
     max_out_len: 32768
     batch_size: 64
     top_k: 20
-    baseline: 96
-    threshold: 3
+    baseline: 100
+    threshold: 5
 
 # ==========================================
 # ACTUAL TEST CASES