{"benchmark_id":"qwenwebbench","benchmark_name":"QwenWebBench","benchmark_description":"QwenWebBench is an internal front-end code generation benchmark by Qwen. It is bilingual (EN/CN) and spans 7 categories (Web Design, Web Apps, Games, SVG, Data Visualization, Animation, and 3D), using auto-render plus a multimodal judge for code and visual correctness. Scores are reported as BT/Elo ratings.","max_score":2000.0,"categories":["multimodal","agents","code"],"modality":"multimodal","total_models":2,"entries":[{"rank":1,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":1568.0,"normalized_score":null,"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},{"rank":2,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":1487.0,"normalized_score":null,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"speed_rps":null,"context_window":262144,"release_date":"2026-04-21","announcement_date":"2026-04-21","multimodal":true,"param_count":27781427952,"is_new":false}]}