List your company

Graduate-level Science Question Answering on GPQA n=546 (test)

100Act ScoreAdaptive Local k-NN Certification (kNN no bias)
48.5261.88575.2588.615Jun 28, 2026

Evaluation results

MethodLinks
Adaptive Local k-NN Certification (kNN no bias)Operating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0610060.539.5511
CRCOperating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0699.96336.9481.2
Selective Pred.Operating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0698.668.431.2411.3
Isotonic Conf.Operating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0696.770.428.6371.3
Calibrated LearnedOperating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0696.666.132.9431.4
ConsensusOperating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.068771.328.7371.8
OracleOperating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0674.5100001.9
Adaptive Local k-NN Certification (Final-round)Operating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0660.982.710.6144
Adaptive Local k-NN CertificationOperating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0653.382.59.4123.1
Confidence Thr.Operating Budget (T)=4, Scaling parameter (λ*)=2.8, Target budget (β)=.77, Training error (eT)=.282026.0650.571.928.1372.8