APEX
AssessPlatforms
A benchmark referenced in the study's coverage map.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 6Hacker News·10/16/2026researchStudy Finds AI Benchmarks Cover Only a Small Share of U.S. Work Tasks
A research project mapped existing AI benchmarks against O*NET occupations and tasks, finding that coverage is concentrated in a limited set of jobs. The authors estimate that about 90% of U.S. working hours are spent on tasks with little or no benchmark coverage, suggesting current benchmarks miss much of the economy's real work.