Mercor estimates 90% of US work hours lack AI benchmark coverage

Mercor, the company founded by Brendan Foody, mapped 29 AI benchmarks to US Department of Labor job tasks and estimates that 90% of US working hours fall on tasks with little or no AI benchmark coverage. The benchmark map, published as part of Mercor's Labor Index research, makes coverage visible at the task level and supports Mercor's expert-data and AI evaluation business.

Mercor estimates 90% of US work hours lack AI benchmark coverage Brendan Foody's company mapped 29 benchmarks to Labor Department job tasks, exposing a gap that also supports Mercor's push into AI evaluation. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published · Updated Primary source: Mercor https://www.mercor.com/research/labor-index/benchmark-map/ Why it matters The map makes benchmark coverage visible at the task level, while its limits show why model scores alone cannot establish readiness for whole jobs. Mercor's push to measure that gap also supports its expert-data and evaluation business. Brendan Foody https://msb.georgetown.edu/news-story/student-experience/brendan-foody-b25-wins-big-east-startup-challenge-for-his-company-seros/?ref=runtimewire built Mercor https://www.mercor.com/?ref=runtimewire around matching people with work. Mercor's estimate that 90% of US working hours https://www.mercor.com/research/labor-index/benchmark-map/?ref=runtimewire fall on tasks with little or no AI benchmark coverage puts a measurement problem at the center of that business: the work AI systems are being judged on still represents a narrow slice of the work people do.…