update explanation of benchmark result table

README.md

@@ -86,18 +86,6 @@ The table below summarizes evaluation results across mathematical tasks and orig
 | **Control LLM***   | 36.0   | 61.7   | **89.7**| 62.5      | 82.5    | 30.8     | **71.6**| 45.4     | **57.6**  | **60.0**    |
 
 ---
-
-### Catastrophic Forgetting on OpenMath
-The following plot illustrates and compares catastrophic forgetting mitigation during training
-
-![Catastrophic Forgetting](plots/ControlLLM_CF_Plot_Math.png)
-
-### Alignment Result
-The plot below highlights the alignment result of the model trained with Control LLM.
-
-![Alignment](plots/alignment_best.png)
-
-
 ### Explanation:
 - **MH**: MathHard
 - **M**: Math
@@ -109,3 +97,13 @@ The plot below highlights the alignment result of the model trained with Control
 - **MLUP**: MMLU Pro
 - **O-Avg**: Original Capability - Average across ARC, GPQA, MMLU, and MLUP
 - **Overall**: Combined average across all tasks
+
+### Catastrophic Forgetting on OpenMath
+The following plot illustrates and compares catastrophic forgetting mitigation during training
+
+![Catastrophic Forgetting](plots/ControlLLM_CF_Plot_Math.png)
+
+### Alignment Result
+The plot below highlights the alignment result of the model trained with Control LLM.
+
+![Alignment](plots/alignment_best.png)