Update README.md

README.md

@@ -145,7 +145,7 @@ The following factors can influence MAI-DS-R1's behavior and performance:
 #### Summary 
 - **General Knowledge & Reasoning**: MAI-DS-R1 performs on par with DeepSeek-R1 and slightly better than R1-1776, especially excelling in mgsm_chain_of_thought_zh, where R1-1776 had a significant regression. 
 
-- **Blocked Topics**: MAI-DS-R1 blocked 99.3% of samples, matching R1-1776, and achieved a higher Satisfaction score, likely due to more relevant responses. 
+- **Blocked Topics**: MAI-DS-R1 unblocked 99.3% of samples, matching R1-1776, and achieved a higher Satisfaction score, likely due to more relevant responses. 
 
 - **Harm Mitigation**: MAI-DS-R1 outperforms both R1-1776 and the original R1 model in minimizing harmful content. 
 ### Model Architecture and Objective