{"benchmark_id":"humaneval-plus","benchmark_name":"HumanEval Plus","benchmark_description":"Enhanced version of HumanEval that extends the original test cases by 80x using EvalPlus framework for rigorous evaluation of LLM-synthesized code functional correctness, detecting previously undetected wrong code","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":0.929,"normalized_score":0.929,"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}]}