{"benchmark_id":"spreadsheetbench-2","benchmark_name":"SpreadsheetBench 2","benchmark_description":"SpreadsheetBench 2 evaluates office automation agents on spreadsheet analysis, reasoning, and manipulation tasks.","max_score":1.0,"categories":["productivity","agents","tool_calling"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"kimi-k3","model_name":"Kimi K3","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.348,"normalized_score":0.348,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":2.85,"output_cost_per_million":14.25,"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":2,"model_id":"ling-3.0-flash-fin","model_name":"Ling 3.0 Flash Fin","organization_name":"InclusionAI","organization_id":"inclusionai","benchmark_score":0.2181,"normalized_score":0.2181,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.06,"output_cost_per_million":0.18,"speed_rps":null,"context_window":262144,"release_date":"2026-09-03","announcement_date":"2026-09-03","multimodal":false,"param_count":124000000000,"is_new":false}]}