{"benchmark_id":"translation-en→set1-spbleu","benchmark_name":"Translation en→Set1 spBleu","benchmark_description":"Translation evaluation using spBLEU (SentencePiece BLEU), a BLEU metric computed over text tokenized with a language-agnostic SentencePiece subword model. Introduced in the FLORES-101 evaluation benchmark for low-resource and multilingual machine translation.","max_score":1.0,"categories":["language"],"modality":"text","total_models":3,"entries":[{"rank":1,"model_id":"nova-pro","model_name":"Nova Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.434,"normalized_score":0.434,"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":"2024-11-20","announcement_date":"2024-11-20","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"nova-lite","model_name":"Nova Lite","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.415,"normalized_score":0.415,"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":"2024-11-20","announcement_date":"2024-11-20","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"nova-micro","model_name":"Nova Micro","organization_name":"Amazon","organization_id":"amazon","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":"2024-11-20","announcement_date":"2024-11-20","multimodal":false,"param_count":null,"is_new":false}]}