{"benchmark_id":"qwenworldbench","benchmark_name":"QwenWorldBench","benchmark_description":"QwenWorldBench is Qwen's internal benchmark for evaluating LLMs as world models that simulate agentic environments across Terminal, SWE, MCP, Search, OS, Android, and Web domains.","max_score":1.0,"categories":["reasoning","simulation","agents"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.621,"normalized_score":0.621,"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":"2026-05-31","announcement_date":"2026-05-31","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.573,"normalized_score":0.573,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":1.25,"output_cost_per_million":3.75,"speed_rps":null,"context_window":1000000,"release_date":"2026-05-19","announcement_date":"2026-05-19","multimodal":false,"param_count":null,"is_new":false}]}