update to reasoning

app.py

@@ -41,7 +41,7 @@ def avg_over_rewardbench(dataframe_core, dataframe_prefs):
     1. Chat: Includes the easy chat subsets (alpacaeval-easy, alpacaeval-length, alpacaeval-hard, mt-bench-easy, mt-bench-medium)
     2. Chat Hard: Includes the hard chat subsets (mt-bench-hard, llmbar-natural, llmbar-adver-neighbor, llmbar-adver-GPTInst, llmbar-adver-GPTOut, llmbar-adver-manual)
     3. Safety: Includes the safety subsets (refusals-dangerous, refusals-offensive, xstest-should-refuse, xstest-should-respond, do not answer)
-    4. Code: Includes the code subsets (hep-cpp, hep-go, hep-java, hep-js, hep-python, hep-rust)
+    4. Reasoning: Includes the code and math subsets (math-prm, hep-cpp, hep-go, hep-java, hep-js, hep-python, hep-rust)
     5. Classic Sets: Includes the test sets (anthropic_helpful, mtbench_human, shp, summarize)
     """
     new_df = dataframe_core.copy()