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 · Published · Updated

Primary source: Mercor

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.

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.

Brendan Foody built Mercor around matching people with work. Mercor's estimate that 90% of US working hours 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.…

Reader comments

Conversation for this story loads after sign-in.