evals.report
BenchmarksLabsCompareRun guides

GDPval

GDPval evaluates AI models agentically (shell + web access via a sandbox harness) on real-world economically valuable knowledge-work deliverables — documents, spreadsheets, slides, diagrams — spanning 44 occupations across 9 major U.S. GDP industries, scored by blind pairwise quality comparison; the Artificial Analysis GDPval-AA variant reports results as an Elo rating.

AgentsEloHigher is better

No run guide for this benchmark yet.