{"benchmark_id":"govreport","name":"GovReport","parent_benchmark":null,"categories":["summarization","long_context"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"A long document summarization dataset consisting of reports from government research agencies including Congressional Research Service and U.S. Government Accountability Office, with significantly longer documents and summaries than other datasets.","paper_link":"https://arxiv.org/abs/2104.02112","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.505282+00:00","updated_at":"2026-07-05T18:27:49.040751+00:00","statistics":{"total_models":2,"average_score":0.2615,"min_score":0.259,"max_score":0.264,"score_stddev":0.0035355339059327407,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.264,"normalized_score":0.264,"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":2,"model_id":"phi-3.5-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.259,"normalized_score":0.259,"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}]}