List your company

Question Answering on MMLU-Pro n=8312 (test) (Act, Acc, WA)

97.6Activation (Act)CRC
26.56845.00963.4581.891Jun 28, 2026

Evaluation results

MethodLinks
CRCbeta=0.15, T=42026.0697.684.814.8
Selective Predictionbeta=0.15, T=42026.0697.385.114.5
Isotonic Confidencebeta=0.15, T=42026.0697.38514.6
Learned Stopperbeta=0.15, T=42026.0696.683.616.4
Calibrated Learnedbeta=0.15, T=42026.0695.985.414
Consensusbeta=0.15, T=42026.0694.584.515.5
Oraclebeta=0.15, T=42026.06861000
Confidence Thresholdbeta=0.15, T=42026.0669.884.515.5
kNN no biasbeta=0.15, T=4, ablated_component=no modulus2026.0637.997.70.9
Adaptive Local k-NN Certification (Ours)beta=0.15, T=42026.0629.8980.6
Final-roundbeta=0.15, T=4, bound_at=t=T2026.0629.397.90.6