Update README.md

README.md

@@ -18,7 +18,7 @@ RoboRefer-2B-SFT is an open-source vision-language model that is instruction-tun
 
 ## How to use
 
-RoboRefer-2B-SFT has strong spatial understanding capability and achieves state-of-the-art performance across diverse benchmarks. Given an image with language instructions, it can not only answer your questions in both qualitative and quantitative ways using its spatial knowledge, but also output precise points for spatial referring to guide robotic control. For more details, please visit our [official repo](https://github.com/Zhoues/RoboRefer).
+RoboRefer-2B-SFT has strong spatial understanding capability and achieves SOTA performance across diverse benchmarks. Given an image with language instructions, it can not only answer your questions in both qualitative and quantitative ways using its spatial knowledge, but also output precise points for spatial referring to guide robotic control. For more details, please visit our [official repo](https://github.com/Zhoues/RoboRefer).
 
 ## Date
 This model was trained in June 2025.