{"benchmark_id":"livesqlbench","benchmark_name":"LiveSQLBench","benchmark_description":"LiveSQLBench evaluates models on generating correct SQL queries against live PostgreSQL databases. The LiveSQLBench-Base-Full v1 dataset contains 600 questions across 22 PostgreSQL databases, testing real-world database reasoning and query generation.","max_score":1.0,"categories":["agents","code"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"minimax-m3","model_name":"MiniMax M3","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.4017,"normalized_score":0.4017,"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}]}