about

src/about.py

@@ -63,11 +63,19 @@ def get_INTRODUCTION_TEXT(model_num: int, LAST_UPDATED: str, paper_link="TODO"):
 
 #TODO 
 INTRODUCE_BENCHMARK = f"""
-<details>
-  <summary style="cursor: pointer; font-size: 18px; color: #2c3e50;">💬 Metric explanations </summary>
-  <p style="color: #2c3e50;">CapArena-Auto is an arena-style automated evaluation benchmark for detailed captioning. It includes 600 evaluation images and assesses model performance through pairwise battles with three baseline models. The final score is calculated by GPT4o-as-a-Judge.</p>
-</details>
-"""
+    <details style="margin: 10px 0; padding: 10px;">
+      <summary style="cursor: pointer; font-size: 18px; color: #2c3e50; font-weight: bold; transition: color 0.3s;">
+        💬 Metric Explanations
+      </summary>
+      <div style="color: #2c3e50; border-left: 4px solid #2980b9; padding-left: 12px; margin-top: 8px;">
+        <p>
+          <strong>CapArena-Auto</strong> is an arena-style automated evaluation benchmark for detailed captioning. 
+          It includes <strong>600 evaluation images</strong> and assesses model performance through 
+          <em>pairwise battles</em> with three baseline models. The final score is calculated by <strong>GPT4o-as-a-Judge</strong>.
+        </p>
+      </div>
+    </details>
+    """
 
 #TODO About
 LLM_BENCHMARKS_TEXT = f"""