Update README.md

README.md

@@ -22,7 +22,7 @@ license_link: https://www.apache.org/licenses/LICENSE-2.0
 - **Model Developers:** Neural Magic
 
 Quantized version of [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
-It achieves an average score of 43.06 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 42.99.
+It achieves an average score of 42.99 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 43.06.
 
 ### Model Optimizations