Update README.md

README.md

@@ -14,7 +14,7 @@ pipeline_tag: text-generation
 
 Over the past three months, we have continued to scale the **thinking capability** of Qwen3-30B-A3B, improving both the **quality and depth** of reasoning. We are pleased to introduce **Qwen3-30B-A3B-Thinking-2507**, featuring the following key enhancements:
 
-- **Significantly improved performance** on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise. Notably, **Qwen3-30B-A3B even outperforms the previous Qwen3-235B-A22B by a large margin**.
+- **Significantly improved performance** on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.
 - **Markedly better general capabilities**, such as instruction following, tool usage, text generation, and alignment with human preferences.
 - **Enhanced 256K long-context understanding** capabilities.