{"benchmark_id":"squality","name":"SQuALITY","parent_benchmark":null,"categories":["summarization","language","long_context"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2205.11465","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.207921+00:00","updated_at":"2026-07-05T18:28:00.711960+00:00","statistics":{"total_models":5,"average_score":0.2124,"min_score":0.188,"max_score":0.243,"score_stddev":0.02726352875179585,"verified_count":0,"self_reported_count":5},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"phi-3.5-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.243,"normalized_score":0.243,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct","analysis_method":"standard evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-23","param_count":3800000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.241,"normalized_score":0.241,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct","analysis_method":"standard evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-23","param_count":60000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"nova-pro","model_name":"Nova Pro","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.198,"normalized_score":0.198,"verified":false,"self_reported":true,"self_reported_source":"https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card","analysis_method":"ROUGE-L","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"nova-lite","model_name":"Nova Lite","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.192,"normalized_score":0.192,"verified":false,"self_reported":true,"self_reported_source":"https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card","analysis_method":"rouge-l","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"nova-micro","model_name":"Nova Micro","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.188,"normalized_score":0.188,"verified":false,"self_reported":true,"self_reported_source":"https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card","analysis_method":"rouge-l","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}