Update README.md

README.md

@@ -109,7 +109,7 @@ print(pipeline([{"role": "user", "content": "Solve x*(sin(x)+2)=0"}]))
 
 ## Training Datasets
 
-This model is trained using [OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) dataset.
+The training corpus for OpenCodeReasoning-7B is [OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) dataset, which is composed of competitive programming questions and DeepSeek-R1 generated responses.
 
 **Data Collection for Training Datasets:**
 
@@ -136,10 +136,9 @@ Data Labeling for Evaluation Datasets:
 
 ### LiveCodeBench (20240801-20250201)
 
-| Models | Pass@1 |
-|:--------------|:------------|
-| R1-Distill-Qwen-7B | 37.6 |
-| OpenCodeReasoning-7B | 51.3 | 
+| Easy  | Medium | Hard | Avg. |
+|:------|:------|:------|:-----|
+| 95.4 | 64.0| 18.0 | 51.3 |
 
 User Prompt Template (without starter code):
 
@@ -167,6 +166,13 @@ You will use the following starter code to write the solution to the problem and
 ```
 ````
 
+### CodeContests
+
+| Public  | Private | Generated | All |
+|:--------|:--------|:----------|:----|
+|   46.7  |   29.6  |    32.3   | 18.1|
+
+
 ## Ethical Considerations:
 
 NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.