{"benchmark_id":"mbpp-evalplus","benchmark_name":"MBPP EvalPlus","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. EvalPlus extends MBPP with significantly more test cases (35x) for more rigorous evaluation of LLM-synthesized code, providing high-quality and precise evaluation.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":2,"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":0.886,"normalized_score":0.886,"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-3.3-70b-instruct","model_name":"Llama 3.3 70B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.876,"normalized_score":0.876,"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":"2024-12-06","announcement_date":"2024-12-06","multimodal":false,"param_count":70000000000,"is_new":false}]}