{"benchmark_id":"aa-briefcase","benchmark_name":"AA-Briefcase","benchmark_description":"AA-Briefcase is an Artificial Analysis evaluation of AI systems on professional knowledge-work tasks, reported as an Elo score.","max_score":3000.0,"categories":["productivity","reasoning","agents"],"modality":"text","total_models":3,"entries":[{"rank":1,"model_id":"grok-4.6","model_name":"Grok 4.6","organization_name":"xAI","organization_id":"xai","benchmark_score":1577.0,"normalized_score":0.526,"verified":false,"self_reported":true,"provider_id":"xai","input_cost_per_million":2.0,"output_cost_per_million":6.0,"speed_rps":null,"context_window":500000,"release_date":"2026-08-12","announcement_date":"2026-08-12","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"kimi-k3","model_name":"Kimi K3","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":1548.0,"normalized_score":0.516,"verified":false,"self_reported":false,"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},{"rank":3,"model_id":"inkling-small","model_name":"Inkling-Small","organization_name":"Thinking Machines Lab","organization_id":"thinking-machines","benchmark_score":917.0,"normalized_score":0.306,"verified":false,"self_reported":true,"provider_id":"thinking-machines","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":256000,"release_date":"2026-07-30","announcement_date":"2026-07-30","multimodal":true,"param_count":276000000000,"is_new":false}]}