Update README.md

README.md

@@ -66,7 +66,7 @@ This approach leverages **verifiable rewards** to enhance reasoning capability a
 # <span id="Performance">3. Model Performance</span>
 For model performance comparison, we benchmark our model against recent reasoning LLMs from the Qwen3 series. 
 All models are evaluated under identical configurations to ensure fairness.
-The results show that our model outperforms the baselines across a range of mainstream benchmarks, including math, science, creative writing, tool use, and human preference alignment.
+The results show that our model outperforms the baselines across a range of mainstream benchmarks, including **math, science, creative writing, tool use, and human preference alignment**.
 
 | Model          | AIME24 | AIME25 | GPQA | Super-GPQA | Science-QA | Writing-Bench | BFCL-V4-Agentic | Arena-hard2 |
 |----------------|--------|--------|------|------------|------------|--------------|----------------|-------------|