AI Benchmarks Ignore 90% of US Working Hours, Mercor Map Finds
90% of US working hours are spent on tasks not covered well by AI benchmarks
Mercor mapped 29 AI benchmarks against 923 US occupations and 18,797 tasks. Only 208 occupations have a task with at least five benchmark prompts, and six of 22 job families have none. The result: roughly 90% of American working hours are spent on tasks with little or no benchmark coverage. Coverage skews toward high-wage, AI-exposed jobs like software engineering and law, leaving legal secretaries, court clerks, and much middle-income knowledge work in the dark.
Our findings suggest that 90% of American working hours are spent on tasks with little or no coverage from existing benchmarks.