Update README.md

README.md

@@ -28,7 +28,7 @@ tags:
 - **Model Developers:** Neural Magic
 
 Quantized version of [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B).
-It achieves an average score of 62.86 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 63.59.
+It achieves an average score of 70.70 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 70.92.
 
 ### Model Optimizations
 
@@ -107,11 +107,11 @@ lm_eval \
   <tr>
    <td>ARC Challenge (25-shot)
    </td>
-   <td>70.92
+   <td>59.39
    </td>
-   <td>70.70
+   <td>59.13
    </td>
-   <td>99.7%
+   <td>99.6%
    </td>
   </tr>
   <tr>