{"task":"Mathematical Reasoning","dataset":"FrontierMath","metric_names":["Accuracy"],"rows":[{"id":120351,"task":"Mathematical Reasoning","parent_task":null,"dataset":"FrontierMath","model_name":"o3","metrics":{"Accuracy":"0.252"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Knowledge Base","uses_additional_data":0,"source":"archive","tags":[]},{"id":120352,"task":"Mathematical Reasoning","parent_task":null,"dataset":"FrontierMath","model_name":"Gemini 1.5 Pro (002)","metrics":{"Accuracy":"0.02"},"paper_url":"https://arxiv.org/abs/2411.04872v5","paper_title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","paper_date":"2024-11-07","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Knowledge Base","uses_additional_data":0,"source":"archive","tags":[]},{"id":120353,"task":"Mathematical Reasoning","parent_task":null,"dataset":"FrontierMath","model_name":"Claude 3.5 Sonnet","metrics":{"Accuracy":"0.01"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Knowledge Base","uses_additional_data":0,"source":"archive","tags":[]},{"id":120354,"task":"Mathematical Reasoning","parent_task":null,"dataset":"FrontierMath","model_name":"o1-preview","metrics":{"Accuracy":"0.01"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Knowledge Base","uses_additional_data":0,"source":"archive","tags":[]},{"id":120355,"task":"Mathematical Reasoning","parent_task":null,"dataset":"FrontierMath","model_name":"o1-mini","metrics":{"Accuracy":"0.01"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Knowledge Base","uses_additional_data":0,"source":"archive","tags":[]},{"id":120356,"task":"Mathematical Reasoning","parent_task":null,"dataset":"FrontierMath","model_name":"GPT-4o","metrics":{"Accuracy":"0.01"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Knowledge Base","uses_additional_data":0,"source":"archive","tags":[]}]}