{"benchmark_id":"squality","benchmark_name":"SQuALITY","benchmark_description":"SQuALITY (Summarization-format QUestion Answering with Long Input Texts, Yes!) is a long-document summarization dataset built by hiring highly-qualified contractors to read public-domain short stories (3000-6000 words) and write original summaries from scratch. Each document has five summaries: one overview and four question-focused summaries. Designed to address limitations in existing summarization datasets by providing high-quality, faithful summaries.","max_score":1.0,"categories":["language","long_context","summarization"],"modality":"text","total_models":5,"entries":[{"rank":1,"model_id":"phi-3.5-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.243,"normalized_score":0.243,"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":"2024-08-23","announcement_date":"2024-08-23","multimodal":false,"param_count":3800000000,"is_new":false},{"rank":2,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.241,"normalized_score":0.241,"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":"2024-08-23","announcement_date":"2024-08-23","multimodal":false,"param_count":60000000000,"is_new":false},{"rank":3,"model_id":"nova-pro","model_name":"Nova Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.198,"normalized_score":0.198,"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":4,"model_id":"nova-lite","model_name":"Nova Lite","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.192,"normalized_score":0.192,"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":5,"model_id":"nova-micro","model_name":"Nova Micro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.188,"normalized_score":0.188,"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}]}