{"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":1,"entries":[{"rank":1,"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":"novita","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":1000000,"release_date":"2026-06-01","announcement_date":"2026-06-01","multimodal":true,"param_count":428000000000,"is_new":false}]}