List your company

Mathematical Reasoning on AIME (test)

0.7766HypervolumeIRT-Router
0.5054720.5758610.646250.716639Sep 29, 2025

Evaluation results

MethodLinks
IRT-RouterEvaluation Protocol=ID (In-distribution)2025.090.7766
RADAREvaluation Protocol=ID (In-distribution)2025.090.776
RouterBenchEvaluation Protocol=ID (In-distribution)2025.090.768
Random-PairEvaluation Protocol=ID (In-distribution)2025.090.5159