GDPval rubrics

GDPval-Rubrics evaluates AI model performance on economically valuable knowledge work tasks drawn from the public GDPval dataset. It uses pointwise scoring based on public rubrics, with the environment aligned to the GDPval-AA scaffolding.

Released

Unknown

Readiness

Paper only

Primary field

Finance & Economics

Benchmark Radar records only publicly supported details and links back to primary sources for verification.