{"benchmark_id":"mbpp-pass@1","benchmark_name":"MBPP pass@1","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. This variant uses pass@1 evaluation metric measuring the percentage of problems solved correctly on the first attempt.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"ministral-8b-instruct-2410","model_name":"Ministral 8B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.7,"normalized_score":0.7,"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":"2024-10-16","announcement_date":"2024-10-16","multimodal":false,"param_count":8019808256,"is_new":false}]}