{"benchmark_id":"crag","name":"CRAG","parent_benchmark":null,"categories":["reasoning","search","finance","economics"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"CRAG (Comprehensive RAG Benchmark) is a factual question answering benchmark consisting of 4,409 question-answer pairs across 5 domains (finance, sports, music, movie, open domain) and 8 question categories. The benchmark includes mock APIs to simulate web and Knowledge Graph search, designed to represent the diverse and dynamic nature of real-world QA tasks with temporal dynamism ranging from years to seconds. It evaluates retrieval-augmented generation systems for trustworthy question answering.","paper_link":"https://arxiv.org/abs/2406.04744","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.589829+00:00","updated_at":"2026-07-05T18:27:46.138338+00:00","statistics":{"total_models":3,"average_score":0.4573333333333333,"min_score":0.431,"max_score":0.503,"score_stddev":0.039703064533274206,"verified_count":0,"self_reported_count":3},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"nova-pro","model_name":"Nova Pro","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.503,"normalized_score":0.503,"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":"accuracy","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":2,"model_id":"nova-lite","model_name":"Nova Lite","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.438,"normalized_score":0.438,"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":"accuracy","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":3,"model_id":"nova-micro","model_name":"Nova Micro","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.431,"normalized_score":0.431,"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":"accuracy","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}]}