diff --git a/.github/workflows/nightly_test_a2.yaml b/.github/workflows/nightly_test_a2.yaml
index 57003ef9..02fd67fe 100644
--- a/.github/workflows/nightly_test_a2.yaml
+++ b/.github/workflows/nightly_test_a2.yaml
@@ -125,7 +125,7 @@ jobs:
           - os: linux-aarch64-a2-4
             model_list:
               - Qwen3-Next-80B-A3B-Instruct
-              - Qwen3-VL-30B-A3B-Instruct
+              - Qwen3-Omni-30B-A3B-Instruct
     uses: ./.github/workflows/_e2e_nightly_single_node_models.yaml
     with:
       vllm: v0.13.0
diff --git a/tests/e2e/models/configs/Qwen3-Omni-30B-A3B-Instruct.yaml b/tests/e2e/models/configs/Qwen3-Omni-30B-A3B-Instruct.yaml
index cdf3866b..6341872d 100644
--- a/tests/e2e/models/configs/Qwen3-Omni-30B-A3B-Instruct.yaml
+++ b/tests/e2e/models/configs/Qwen3-Omni-30B-A3B-Instruct.yaml
@@ -5,7 +5,7 @@ tasks:
 - name: "mmmu_val"
   metrics:
   - name: "acc,none"
-    value: 0.52
+    value: 0.60
 max_model_len: 8192
 tensor_parallel_size: 4
 enable_expert_parallel: True