{"benchmark_id":"webarena-verified","benchmark_name":"WebArena-Verified","benchmark_description":"WebArena-Verified evaluates browser agents on realistic web tasks using a verified task set and execution-based grading.","max_score":1.0,"categories":["multimodal","agents","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qwen3.8-27b","model_name":"Qwen3.8-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.648,"normalized_score":0.648,"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":"2026-08-14","announcement_date":"2026-08-14","multimodal":true,"param_count":27781427952,"is_new":false}]}