evaluation-task · Source-linked discovery
GDPval
GDPval measures model performance on economically valuable, real-world tasks across 44 occupations.
OriginTejal Patwardhan, Rachel Dias, Elizabeth Proehl et al.TopicsGeneral capabilityStatusimported
Can support
Not independently assessed by FronteraEval yet.
Cannot support by itself
No inference beyond the upstream source should be made until the protocol is reviewed.