{"benchmark_id":"mm-mind2web","name":"MM-Mind2Web","parent_benchmark":null,"categories":["multimodal","reasoning","frontend_development","agents"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"A multimodal web navigation benchmark comprising 2,000 open-ended tasks spanning 137 websites across 31 domains. Each task includes HTML documents paired with webpage screenshots, action sequences, and complex web interactions.","paper_link":"https://arxiv.org/abs/2306.06070","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.567612+00:00","updated_at":"2026-07-05T18:27:53.668844+00:00","statistics":{"total_models":3,"average_score":0.6006666666666667,"min_score":0.558,"max_score":0.637,"score_stddev":0.0398789836045671,"verified_count":0,"self_reported_count":3},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"nova-pro","model_name":"Nova Pro","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.637,"normalized_score":0.637,"verified":false,"self_reported":true,"self_reported_source":"https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card","analysis_method":"step accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"nova-lite","model_name":"Nova Lite","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.607,"normalized_score":0.607,"verified":false,"self_reported":true,"self_reported_source":"https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card","analysis_method":"accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"qwen3-coder-480b-a35b-instruct","model_name":"Qwen3-Coder 480B A35B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.558,"normalized_score":0.558,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3-coder/","analysis_method":"Agentic Browser Use benchmark","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-31","param_count":480000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}