evaluation-task · Source-linked discovery
GPQA: Graduate-Level STEM Knowledge Challenge
Contains challenging multiple-choice questions created by domain experts in biology, physics, and chemistry, designed to test advanced scientific understanding beyond basic internet searches. Experts at PhD level in the corresponding domains reach 65% accuracy.
OriginDavid Rein, Betty Li Hou, Asa Cooper Stickland 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.