openai models

benchmark_data.csv

@@ -1,5 +1,5 @@
 Model,Solved_Problems,Total_Problems,Class1_Solved,Class2_Solved,Class3_Solved,Class4_Solved
-Meta-Llama-3.1-8B-Instruct,150,600,123,25,2,0
+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
@@ -8,4 +8,11 @@ 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
-Meta-Llama-3.1-8B-Instruct-induction-mixed,251,600,143,85,22,1
+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
+