diff --git a/.buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh b/.buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh
index 614642fed2e2a..2f04cc1283df3 100644
--- a/.buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh
+++ b/.buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh
@@ -47,5 +47,5 @@ done
 
 lm_eval --model vllm \
   --model_args pretrained=$MODEL,tensor_parallel_size=$TP_SIZE,add_bos_token=true,distributed_executor_backend="ray",trust_remote_code=true,max_model_len=4096 \
-  --tasks ifeval --num_fewshot $FEWSHOT --limit $LIMIT \
+  --tasks gsm8k --num_fewshot $FEWSHOT --limit $LIMIT \
   --batch_size $BATCH_SIZE