{"benchmark_id":"osworld-extended","benchmark_name":"OSWorld Extended","benchmark_description":"OSWorld is a scalable, real computer environment benchmark for evaluating multimodal agents on open-ended tasks across Ubuntu, Windows, and macOS. It comprises 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows. The benchmark evaluates agents' ability to interact with computer interfaces using screenshots and actions in realistic computing environments.","max_score":1.0,"categories":["multimodal","reasoning","general","agents"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"claude-3-5-sonnet-20241022","model_name":"Claude 3.5 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.22,"normalized_score":0.22,"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":"2024-10-22","announcement_date":"2024-10-22","multimodal":true,"param_count":null,"is_new":false}]}