update table

benchmark_data.csv

@@ -1,18 +1,19 @@
-Model,Solved_Problems,Total_Problems,Logic Basic Solved,Logic Easy Solved,Logic Medium Solved,Logic Hard Solved
-Llama-3.1-8B-Instruct,150,600,123,25,2,0
-CodeLlama-34b-Instruct-hf,104,600,102,2,0,0
-QwQ-32B-Preview,139,600,115,23,0,1
-Internlm2-20b,116,600,106,10,0,0
-Llama-3.2-3B-Instruct,48,600,47,1,0,0
-Mixtral-8x7B-Instruct-v0.1,93,600,91,2,0,0
-Qwen2-57B-A14B-Instruct,118,600,107,11,0,0
-Llama-3.3-70B-Instruct,154,600,126,25,2,1
-DeepSeek-R1-Distill-Llama-70B,242,600,133,92,13,4
-Llama-3.1-8B-Instruct-induction-mixed,251,600,143,85,22,1
-o1,356,600,138,133,62,23
-o1-mini,302,600,145,123,30,4
-o3-mini,347,600,146,135,55,11
-gpt-4o,202,600,135,56,9,2
-gpt-4.5-preview,215,600,142,61,9,3
-o4-mini,369,600,140,132,78,19
+Model,Logical Power Ranking,Logical Power Score,Solved Problems,Total Problems,Logic Basic Solved,Logic Easy Solved,Logic Medium Solved,Logic Hard Solved
+o4-mini,1,12.3,369,600,140,132,78,19
+o1,2,11.9,356,600,138,133,62,23
+o3-mini,3,11.6,347,600,146,135,55,11
+o1-mini,4,10.1,302,600,145,123,30,4
+gemini-2.0-flash-thinking-exp-01-21,5,8.6,258,600,139,97,20,2
+DeepSeek-R1-Distill-Llama-70B,6,8.1,242,600,133,92,13,4
+gpt-4.5-preview,7,7.2,215,600,142,61,9,3
+gpt-4o,8,6.7,202,600,135,56,9,2
+Llama-3.3-70B-Instruct,9,5.1,154,600,126,25,2,1
+Llama-3.1-8B-Instruct,10,5.0,150,600,123,25,2,0
+QwQ-32B-Preview,11,4.6,139,600,115,23,0,1
+Internlm2-20b,12,3.9,116,600,106,10,0,0
+Qwen2-57B-A14B-Instruct,13,3.9,118,600,107,11,0,0
+CodeLlama-34b-Instruct-hf,14,3.5,104,600,102,2,0,0
+Mixtral-8x7B-Instruct-v0.1,15,3.1,93,600,91,2,0,0
+Llama-3.2-3B-Instruct,16,1.6,48,600,47,1,0,0
+