What it means
A fixed set of test questions used to compare models, with a published score for each. Experts are hired to write questions hard enough that current models get them wrong.
Used in: Expert roles in maths, science, law, medicine and coding.
In open roles right now
407 of the open roles we list mention “benchmark” in the title or description, on 32 platforms (as of 23 October 2026). Of those that state an hourly rate (151 distinct postings), the median is $70/hr, and the middle half pay $50 to $90.
Most of them on: Mercor (53), Turing (51), Sepal AI (39), Mindrift (38), Weekday (37), Alignerr (33), and 26 more.
Pharmacists: Paid Expert Review for Clinical AI Benchmarks (posted today)Terac·United States·Flexible hours
$90 per taskToday
Genomics & Cell Biology SpecialistMercor·United Kingdom, United States·Part-time·PhD
$70–100/hr1 day ago
Pod Lead — Material Sciences (Terminal Bench Science)Turing·Location not stated·Full-time·PhD
Pay set per project1 day ago
Junior Lawyermicro1·Location not stated
$50–80/hr1 day ago