Update README.md

README.md

@@ -102,7 +102,7 @@ The model was evaluated on reasoning tasks including AIME24, MMLU_COT, and GSM8K
 
 ### Reproduction
 
-The results of AIME24 and MMLU_COT were obtained using [SGLang](https://docs.sglang.ai/) via forked [lm-evaluation-harness](https://github.com/BowenBao/lm-evaluation-harness/tree/cot).
+The results of AIME24 and MMLU_COT were obtained using [SGLang](https://docs.sglang.ai/) while the result of GSM8K were obtained using [vLLM](https://docs.vllm.ai/en/latest/). All the evaluations were conducted via forked [lm-evaluation-harness](https://github.com/BowenBao/lm-evaluation-harness/tree/cot).
 
 ### AIME24
 ```
@@ -146,7 +146,6 @@ lm_eval --model local-completions \
     --output_path output_data/mmmlu_cot 2>&1 | tee logs/mmmlu_cot.log
 ```
 
-The result of GSM8K were obtained using [vLLM](https://docs.vllm.ai/en/latest/) via forked [lm-evaluation-harness](https://github.com/BowenBao/lm-evaluation-harness/tree/cot).
 
 ### GSM8K
 ```