Update README.md

README.md

@@ -51,7 +51,7 @@ LandAI-Base demonstrates a substantial leap in reasoning capabilities compared t
 | GPT-4o | 92.1% | 9.3% | 90.2% | 51.9% |
 | Gemini 2.5 Pro | 98.3% | 92.0% | - | 71.2% |
 
-> **Note**: As shown in Extended Data Table 2 of the paper, LandAI-Base achieves a **2.5x improvement** in geographic reasoning and a **5x improvement** in mathematical logic over the vanilla baseline.
+
 
 ## 📂 Dataset Composition