{"benchmark_id":"corpusqa","benchmark_name":"CorpusQA","benchmark_description":"CorpusQA is a multi-document, free-form long-context question answering benchmark in which a model must retrieve and reason over information distributed across a large corpus to produce open-ended answers that are scored by an LLM judge.","max_score":1.0,"categories":["long_context","reasoning","general"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"mai-thinking-1","model_name":"MAI-Thinking-1","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.82,"normalized_score":0.82,"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":"2026-06-02","announcement_date":"2026-06-02","multimodal":false,"param_count":1000000000000,"is_new":false}]}