Update README.md

README.md

@@ -76,22 +76,11 @@ The training corpus for OpenCodeReasoning-CPP-Nemotron-32B is [OpenCodeReasoning
 
 
 ## Evaluation Dataset
-We used the datasets listed in the next section to evaluate OpenCodeReasoning-CPP-Nemotron-32B. <br>
+We used the [IOI benchmark](https://huggingface.co/datasets/open-r1/ioi) to evaluate OpenCodeReasoning-CPP-Nemotron-32B. <br>
 * Data Collection Method: Hybrid: Automated, Human, Synthetic <br>
 * Data Labeling Method: Hybrid: Automated, Human, Synthetic <br>
 
 
-### [LiveCodeBench](https://huggingface.co/datasets/livecodebench/code_generation_lite)
-| Easy  | Medium | Hard | Avg. |
-|:------|:------|:------|:-----|
-| 98.4  | 77.2  | 30.4  | 61.7 |
-
-### [CodeContests](https://huggingface.co/datasets/deepmind/code_contests)
-| Public  | Private | Generated | All |
-|:--------|:--------|:----------|:----|
-|   60.3  |   36.6  |    42.7   | 24.4|
-
-
 ## Inference
 - **Engine:** vLLM <br>
 - **Test Hardware** NVIDIA H100-80GB <br>