{"benchmark_id":"vibe-pro","name":"VIBE-Pro","parent_benchmark":{"id":"vibe","name":"VIBE"},"categories":["agents","code"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"VIBE-Pro is an advanced version of the VIBE (Visual & Interactive Benchmark for Execution) benchmark that evaluates LLMs on professional-grade full-stack application development tasks. It measures model performance across complex real-world development scenarios including web, mobile, and backend applications with higher difficulty than the standard VIBE benchmark.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.696894+00:00","updated_at":"2026-07-05T18:28:04.450838+00:00","statistics":{"total_models":2,"average_score":0.549,"min_score":0.542,"max_score":0.556,"score_stddev":0.009899494936611674,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.556,"normalized_score":0.556,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/models/text/m27","analysis_method":null,"verification_date":null,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":204800,"announcement_date":"2026-03-18","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"MiniMax","best_throughput":null,"throughput_provider":"MiniMax","context_provider":"Novita"},{"rank":2,"model_id":"minimax-m2.5","model_name":"MiniMax M2.5","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.542,"normalized_score":0.542,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/news/minimax-m25","analysis_method":"Average across VIBE-Pro categories","verification_date":null,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2026-02-12","param_count":230000000000,"is_open_source":true,"is_new":false,"best_latency":3.0,"latency_provider":"MiniMax","best_throughput":100.0,"throughput_provider":"MiniMax","context_provider":"MiniMax"}]}