Update README.md

README.md

@@ -41,3 +41,12 @@ We evaluated GLM-4.6 across eight public benchmarks covering agents, reasoning,
 **Both GLM-4.5 and GLM-4.6 use the same inference method.**
 
 you can check our [github](https://github.com/zai-org/GLM-4.5) for more detail.
+
+## Recommended Evaluation Parameters
+
+For general evaluations, we recommend using a **sampling temperature of 1.0**.  
+
+For **code-related evaluation tasks** (such as LCB), it is further recommended to set:
+
+- `top_p = 0.95`
+- `top_k = 40`