{"benchmark_id":"androidbench","benchmark_name":"AndroidBench","benchmark_description":"AndroidBench evaluates coding agents on Android application development tasks.","max_score":1.0,"categories":["agents","code","tool_calling"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qwen3.8-max","model_name":"Qwen3.8 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.751,"normalized_score":0.751,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":1.65,"output_cost_per_million":4.951,"speed_rps":null,"context_window":256000,"release_date":"2026-08-02","announcement_date":"2026-08-02","multimodal":true,"param_count":2400000000000,"is_new":false}]}