Update README.md

README.md

@@ -34,7 +34,7 @@ The benchmark results demonstrate a level of performance that significantly surp
 
 | Model                               | HumanEval Pass@1 Score | Note                   |
 | :---------------------------------- | :--------------------: | :--------------------- |
-| **moelanoby/phi3-M3-V2 (This Model)** |       **98.17%**       | **Commercial License** |
+| **moelanoby/phi3-M3-V2 (This Model)** |       **95.12%/98.17%/98.56%**       | **Commercial License** and they are ordered with 0,1,2 self corrections |
 | GPT-4.5 / "Orion"                   |       `~96.00%`        | Projected (Late 2025)  |
 | Gemini 2.5 Pro                      |       `~95.00%`        | Projected (Late 2025)  |
 | Claude 4                            |       `~94.00%`        | Projected (Late 2025)  |
@@ -121,7 +121,9 @@ except AttributeError:
 
 # (Example generation code would follow here)
 ```
-
+## HUGE NOTES
+- downside: the model might grow more incoherent and less accurate as you add more self corrections
+- recommendations: you could use 1,2,3 self corrections if needed and 2 self corrections is the most recommended 
 ## Acknowledgements
 
 -   The base of this model utilizes the **Phi-3** architecture developed by Microsoft.