Update README.md

README.md

@@ -17,7 +17,7 @@ GitVac is like a vacuum cleaner for code fixes. It's a series of 3B, 8B, 14B, an
 
 # Training Data 
 *The data to train the models came from r1 outputs via distalation.*
-However to gauge accuracuy of the model o3/r1 were used to do eval with the same prompts.
+However to gauge accuracuy of the model o3/r1 were used to do eval with the same prompts. 
 
 # How is verification done?
 A lot of models are already trained on function calling syntax. 
@@ -354,6 +354,8 @@ Tested against the remainder 1300 r1 could not pass. These datasets were never s
 
 | Model | Success Rate | Notes |
 |-------|--------------|-------|
+| O3 | 30% | used for eval |
+| R1 | 15% | used for eval/training |
 | GitVac-3B-Turbo | 42% | Fast but not accurate. Missing tags in outputs. |
 | Llama-GitVac-7B-Turbo | 90% | Sweet spot for speed/quality/cost. No think tags. |
 | GitVac-R-14B | 92% | Excellent reasoning capabilities for price/speed |