List your company

Tutor Robustness Evaluation on Student w/ Reasoning

16Student LeakageMathDial-SFT
14.6823.5932.541.41Apr 20, 2026

Evaluation results

MethodLinks
MathDial-SFTTutor Setting=Base in-context2026.04165.46445.45
SocraticLMTutor Setting=Base in-context2026.04294.96382.46
TutorRL-7BTutor Setting=Base in-context2026.04495.78298.6