{"benchmark_id":"humanevalfim-average","benchmark_name":"HumanEvalFIM-Average","benchmark_description":"Average evaluation of HumanEval Fill-in-the-Middle benchmark variants (single-line, multi-line, random-span) for assessing code infilling capabilities of language models","max_score":1.0,"categories":["general"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"codestral-22b","model_name":"Codestral-22B","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.916,"normalized_score":0.916,"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":"2024-05-29","announcement_date":"2024-05-29","multimodal":false,"param_count":22200000000,"is_new":false}]}