OSWorld 2.1
A benchmark for evaluating AI model performance on enterprise desktop operating system automation tasks, covering GUI operations and system-level task execution.
Core Facts
Timeline (last 90 days)
While generating the OSWorld 2.1 reference runs, Simular had tasks stop after one step due to the model key's usage limit, yet they were recorded as successful with a score of 0, and the average score over the whole folder was computed as 0.40.
Claude Sonnet 5.5 reaches 80.1% on the OSWorld 2.1 enterprise desktop operation benchmark.
All Facts (3)
OSWorld 2.0 contains 108 long-workflow real computer tasks, with a median completion time of 1.6 hours for skilled humans, approximately 48 times that of version 1.0 (2 minutes).
65%UnverifiedClaude Sonnet 5.5 reaches 80.1% on the OSWorld 2.1 enterprise desktop operation benchmark.
50%UnverifiedWhile generating the OSWorld 2.1 reference runs, Simular had tasks stop after one step due to the model key's usage limit, yet they were recorded as successful with a score of 0, and the average score over the whole folder was computed as 0.40.
50%