{"benchmark_id":"corpusqa-1m","name":"CorpusQA 1M","parent_benchmark":null,"categories":["long_context","reasoning","general"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"CorpusQA 1M is a long-context question answering benchmark designed to evaluate models at approximately 1 million token contexts. Models are scored on accuracy when retrieving and reasoning over information distributed across an extremely long input corpus.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.522018+00:00","updated_at":"2026-09-02T17:08:00.350827+00:00","statistics":{"total_models":3,"average_score":0.606,"min_score":0.593,"max_score":0.62,"score_stddev":0.013527749258468665,"verified_count":0,"self_reported_count":3},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"deepseek-v4-pro-max","model_name":"DeepSeek-V4-Pro-Max","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.62,"normalized_score":0.62,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-23","param_count":1600000000000,"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":"deepseek-v4-flash-max","model_name":"DeepSeek-V4-Flash-Max","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.605,"normalized_score":0.605,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","analysis_method":"Accuracy","verification_date":null,"provider_id":"deepseek","input_cost_per_million":0.14,"output_cost_per_million":0.28,"context_window":1048576,"announcement_date":"2026-04-23","param_count":284000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepSeek","best_throughput":null,"throughput_provider":"DeepSeek","context_provider":"DeepSeek"},{"rank":3,"model_id":"deepseek-v4-flash-0423","model_name":"DeepSeek-V4-Flash-0423","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.593,"normalized_score":0.593,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","analysis_method":"Accuracy","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.2,"context_window":1048576,"announcement_date":"2026-04-23","param_count":284000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"Novita"}]}