Update README.md

README.md

@@ -10,7 +10,7 @@ The extrapolated (ExPO) model based on [`UCLA-AGI/Mistral7B-PairRM-SPPO`](https:
 
 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 **35.4%** win rate and **31.8%** LC win rate on **AlpacaEval 2.0**.
+This extrapolated model achieves the **35.4%** win rate and **31.8%** LC win rate on **AlpacaEval 2.0**, outperforming the original `Mistral7B-PairRM-SPPO`'s 32.2% and 30.5%, respectively.
 
 ## Evaluation Results