List your company

Uncertainty Quantification on GSM8K (test)

84.04AUROCCAGE-CAL
55.585662.972870.3677.7472May 28, 2026

Evaluation results

MethodLinks
CAGE-CALRollouts=3, Topologies=52026.0584.0497.51
Plurality voteRollouts=3, Topologies=52026.0584.0197.87
DAERollouts=3, Topologies=52026.0582.6197.72
Answer entropyRollouts=3, Topologies=52026.0582.697.72
Avg-logprobRollouts=3, Topologies=52026.0557.8775.41
MATURollouts=3, Topologies=52026.0556.6895.45