{"benchmark_id":"mbpp-plus","benchmark_name":"MBPP Plus","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 for more rigorous evaluation.","max_score":1.0,"categories":["reasoning","code"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"mistral-small-3.2-24b-instruct-2506","model_name":"Mistral Small 3.2 24B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.7833,"normalized_score":0.7833,"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":"2025-06-20","announcement_date":"2025-06-20","multimodal":true,"param_count":23600000000,"is_new":false}]}