{"benchmark_id":"mobileminiwob++-sr","benchmark_name":"MobileMiniWob++_SR","benchmark_description":"MobileMiniWob++ SR (Success Rate) is an adaptation of the MiniWob++ web interaction benchmark for mobile Android environments within AndroidWorld. It comprises 92 web interaction tasks adapted for touch-based mobile interfaces, evaluating agents' ability to navigate and interact with web applications on mobile devices.","max_score":1.0,"categories":["multimodal","frontend_development","agents"],"modality":"multimodal","total_models":2,"entries":[{"rank":1,"model_id":"qwen2.5-vl-7b","model_name":"Qwen2.5 VL 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.914,"normalized_score":0.914,"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":"2025-01-26","announcement_date":"2025-01-26","multimodal":true,"param_count":8290000000,"is_new":false},{"rank":2,"model_id":"qwen2.5-vl-72b","model_name":"Qwen2.5 VL 72B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.68,"normalized_score":0.68,"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":"2025-01-26","announcement_date":"2025-01-26","multimodal":true,"param_count":72000000000,"is_new":false}]}