{"benchmark_id":"bankertoolbench","benchmark_name":"BankerToolBench","benchmark_description":"BankerToolBench is a public benchmark that evaluates models on banking and finance tool-use tasks. Models are scored against dataset rubrics, measuring their ability to correctly invoke tools and complete multi-step financial workflows.","max_score":1.0,"categories":["finance","agents","tool_calling"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"hy4-preview","model_name":"Hy4 preview","organization_name":"Tencent","organization_id":"tencent","benchmark_score":0.786,"normalized_score":0.786,"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":"2026-08-28","announcement_date":"2026-08-28","multimodal":false,"param_count":770000000000,"is_new":false},{"rank":2,"model_id":"minimax-m3","model_name":"MiniMax M3","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.7612,"normalized_score":0.7612,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.28,"output_cost_per_million":1.1,"speed_rps":null,"context_window":524288,"release_date":"2026-06-01","announcement_date":"2026-06-01","multimodal":true,"param_count":428000000000,"is_new":false}]}