{"benchmark_id":"vatex","benchmark_name":"VATEX","benchmark_description":"VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research. Contains over 41,250 videos and 825,000 captions in both English and Chinese, with over 206,000 English-Chinese parallel translation pairs. Supports multilingual video captioning and video-guided machine translation tasks.","max_score":1.0,"categories":["language","multimodal","video","vision"],"modality":"multimodal","total_models":2,"entries":[{"rank":1,"model_id":"nova-lite","model_name":"Nova Lite","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.778,"normalized_score":0.778,"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-pro","model_name":"Nova Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.778,"normalized_score":0.778,"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}]}