diff --git a/tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2-MTP.yaml b/tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2-MTP.yaml
index d247515a0f0..921365ae686 100644
--- a/tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2-MTP.yaml
+++ b/tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2-MTP.yaml
@@ -3,8 +3,9 @@ accuracy_threshold: 0.88
 tolerance: 0.03
 num_questions: 1319
 num_fewshot: 5
+max_tokens: 12000
 server_args: >-
-  --max-model-len 4096
+  --max-model-len 16384
   --data-parallel-size 2
   --enable-expert-parallel
   --max-num-seqs 384