Update README.md

README.md

@@ -10,7 +10,7 @@ The extrapolated (ExPO) model based on [`princeton-nlp/Llama-3-Instruct-8B-SimPO
 
 Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
 
-This model achieves the **40.6%** win rate and **45.8%** LC win rate on **AlpacaEval 2.0**.
+This extrapolated model achieves the **40.6%** win rate and **45.8%** LC win rate on **AlpacaEval 2.0**, outperforming the original `Llama-3-Instruct-8B-SimPO`'s 40.5% and 44.7%, respectively.
 
 ## Evaluation Results