{"benchmark_id":"mbpp-++-base-version","benchmark_name":"MBPP ++ base version","benchmark_description":"MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality. This is an enhanced version with additional test cases.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"llama-3.1-70b-instruct","model_name":"Llama 3.1 70B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.86,"normalized_score":0.86,"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":"2024-07-23","announcement_date":"2024-07-23","multimodal":false,"param_count":70000000000,"is_new":false}]}