{"benchmark_id":"surds","benchmark_name":"SURDS","benchmark_description":"SURDS is a benchmark for spatial understanding and reasoning in autonomous-driving scenes.","max_score":1.0,"categories":["multimodal","reasoning","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.772,"normalized_score":0.772,"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}]}