Update README.md

README.md

@@ -37,7 +37,7 @@ We achieved this through machine-generated task vectors that optimize thinking p
 - **🎯 Focused Reasoning**: Machine-generated task vectors optimize thinking processes for search tasks
 
 ## Evaluation
-Following the same MCP benchmark methodology used for [Jan-Nano](https://huggingface.co/Menlo/Jan-nano) and [Jan-Nano-128k](https://huggingface.co/Menlo/Jan-nano-128k), Lucy demonstrates impressive performance despite being only a 1.7B model, achieving higher accuracy than DeepSeek-v3 on MCP tasks.
+Following the same MCP benchmark methodology used for [Jan-Nano](https://huggingface.co/Menlo/Jan-nano) and [Jan-Nano-128k](https://huggingface.co/Menlo/Jan-nano-128k), Lucy demonstrates impressive performance despite being only a 1.7B model, achieving higher accuracy than DeepSeek-v3 on [SimpleQA](https://openai.com/index/introducing-simpleqa/).
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/lG2FqLCWXq1N8lh7wlJgW.png)