{"benchmark_id":"vibe-pro","benchmark_name":"VIBE-Pro","benchmark_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.","max_score":1.0,"categories":["agents","code"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.556,"normalized_score":0.556,"verified":false,"self_reported":true,"provider_id":"fireworks","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":196608,"release_date":"2026-03-18","announcement_date":"2026-03-18","multimodal":false,"param_count":null,"is_new":false},{"rank":2,"model_id":"minimax-m2.5","model_name":"MiniMax M2.5","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.542,"normalized_score":0.542,"verified":false,"self_reported":true,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":100.0,"context_window":1000000,"release_date":"2026-02-12","announcement_date":"2026-02-12","multimodal":false,"param_count":230000000000,"is_new":false}]}