{"benchmark_id":"multipl-e-mbpp","benchmark_name":"Multipl-E MBPP","benchmark_description":"MultiPL-E extends the Mostly Basic Python Problems (MBPP) benchmark to 18+ programming languages for evaluating multilingual code generation capabilities. MBPP contains 974 crowd-sourced programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality. Each problem includes a task description, code solution, and automated test cases.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":3,"entries":[{"rank":1,"model_id":"llama-3.1-405b-instruct","model_name":"Llama 3.1 405B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.657,"normalized_score":0.657,"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":405000000000,"is_new":false},{"rank":2,"model_id":"llama-3.1-70b-instruct","model_name":"Llama 3.1 70B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.62,"normalized_score":0.62,"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},{"rank":3,"model_id":"llama-3.1-8b-instruct","model_name":"Llama 3.1 8B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.524,"normalized_score":0.524,"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":8000000000,"is_new":false}]}