{"benchmark_id":"french-mmlu","benchmark_name":"French MMLU","benchmark_description":"French version of MMLU-Pro, a multilingual benchmark for evaluating language models' cross-lingual reasoning capabilities across 14 diverse domains including mathematics, physics, chemistry, law, engineering, psychology, and health.","max_score":1.0,"categories":["language","legal","reasoning","finance","general","healthcare"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"ministral-8b-instruct-2410","model_name":"Ministral 8B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.575,"normalized_score":0.575,"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":"2024-10-16","announcement_date":"2024-10-16","multimodal":false,"param_count":8019808256,"is_new":false}]}