List your company

Tool-Integrated Reasoning on AIME 24 (test accuracy)

43.85Test AccuracySeq-ALP
35.082837.358939.63541.9111Mar 19, 2026

Evaluation results

MethodLinks
Seq-ALPtemperature=1.0, sampling=average@32, multi-turn=true2026.0343.85
Token-MIStemperature=1.0, sampling=average@32, multi-turn=true2026.0339.48
Seq-MIStemperature=1.0, sampling=average@32, multi-turn=true2026.0339.48
Token-ALPtemperature=1.0, sampling=average@32, multi-turn=true2026.0338.65
Seq-Bypasstemperature=1.0, sampling=average@32, multi-turn=true2026.0337.19
GRPOtemperature=1.0, sampling=average@32, multi-turn=true2026.0335.42