{"benchmark_id":"deck-bench","benchmark_name":"DECK-Bench","benchmark_description":"DECK-Bench is Moonshot AI's internal evaluation of agents on creating and reasoning over presentation-style knowledge-work artifacts.","max_score":1.0,"categories":["productivity","reasoning","agents"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"kimi-k3","model_name":"Kimi K3","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.735,"normalized_score":0.735,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":null,"context_window":1048576,"release_date":"2026-07-16","announcement_date":"2026-07-16","multimodal":true,"param_count":2800000000000,"is_new":false}]}