BenchmarkOSWorld
OSWorld 2.0
计算机操作基准，模拟用户在真实操作系统界面上执行跨应用任务，涉及截图理解、GUI元素定位和多步骤执行
Timeline (last 90 days)
Sep 28
GPT-6 Astra has set new records on the Terminal-Bench 4.0 and OSWorld 2.0 benchmarks.
Unverified50%
Sep 28
OSWorld 2.0 simulates a complete desktop operating system environment and tests a model's ability to complete complex tasks through screenshot perception, GUI interaction, and cross-application collaboration.
Unverified50%
All Facts (2)
Unverified
GPT-6 Astra has set new records on the Terminal-Bench 4.0 and OSWorld 2.0 benchmarks.
50%UnverifiedOSWorld 2.0 simulates a complete desktop operating system environment and tests a model's ability to complete complex tasks through screenshot perception, GUI interaction, and cross-application collaboration.
50%