List your company

Tool-Integrated Reasoning on AIME 25 (test accuracy)

31.25Test AccuracyToken-ALP
23.772425.713727.65529.5963Mar 19, 2026

Evaluation results

MethodLinks
Token-ALPtemperature=1.0, sampling=average@32, multi-turn=true2026.0331.25
Token-MIStemperature=1.0, sampling=average@32, multi-turn=true2026.0328.85
Seq-ALPtemperature=1.0, sampling=average@32, multi-turn=true2026.0328.65
GRPOtemperature=1.0, sampling=average@32, multi-turn=true2026.0324.79
Seq-MIStemperature=1.0, sampling=average@32, multi-turn=true2026.0324.17
Seq-Bypasstemperature=1.0, sampling=average@32, multi-turn=true2026.0324.06