{"benchmark_id":"sat-math","benchmark_name":"SAT Math","benchmark_description":"SAT Math benchmark from AGIEval containing standardized mathematics questions from the College Board SAT examination, designed to evaluate mathematical reasoning capabilities of foundation models using human-centric assessment methods.","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"gpt-4-0613","model_name":"GPT-4","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.89,"normalized_score":0.89,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2023-06-13","announcement_date":"2023-06-13","multimodal":true,"param_count":null,"is_new":false}]}