Update README.md

README.md

@@ -522,7 +522,8 @@ Consider the **Qwen2.5-VL-3B-Instruct** evaluation:
 
 <img src="https://cdn-uploads.huggingface.co/production/uploads/647777304ae93470ffc28913/smkynrig5uQiiEAbcqFWg.png" width="800"/>
 
-The following table highlights evaluation results where **SpaceOm** outperformed the **Qwen2.5-VL-3B-Instruct** base model
+The following table highlights evaluation results where **SpaceOm** outperformed the **Qwen2.5-VL-3B-Instruct** base model, averaging **41.48 %** accuracy over 
+the tested cog map output settings.
 
 
 | Config               | Overall | Rotation | Among | Around |