{"benchmark_id":"mbpp+","benchmark_name":"MBPP+","benchmark_description":"MBPP+ is an enhanced version of MBPP (Mostly Basic Python Problems) with significantly more test cases (35x) for more rigorous evaluation. MBPP is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":4,"entries":[{"rank":1,"model_id":"mimo-v2.5-pro","model_name":"MiMo-V2.5-Pro","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.741,"normalized_score":0.741,"verified":false,"self_reported":true,"provider_id":"xiaomi","input_cost_per_million":0.435,"output_cost_per_million":0.87,"speed_rps":null,"context_window":1048576,"release_date":"2026-04-27","announcement_date":"2026-04-27","multimodal":false,"param_count":1023244718976,"is_new":false},{"rank":2,"model_id":"qwen-2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.672,"normalized_score":0.672,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":32500000000,"is_new":false},{"rank":3,"model_id":"qwen-2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.632,"normalized_score":0.632,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":14700000000,"is_new":false},{"rank":4,"model_id":"ernie-4.5","model_name":"ERNIE 4.5","organization_name":"Baidu","organization_id":"baidu","benchmark_score":0.402,"normalized_score":0.402,"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":"2025-06-25","announcement_date":"2025-06-25","multimodal":false,"param_count":21000000000,"is_new":false}]}