List your company

Tool-Integrated Reasoning on Minerva Math

43.18Test AccuracyToken-ALP
39.051240.123141.19542.2669Mar 19, 2026

Evaluation results

MethodLinks
Token-ALPtemperature=1.0, sampling=average@32, multi-turn=true2026.0343.18
Seq-ALPtemperature=1.0, sampling=average@32, multi-turn=true2026.0343.1
GRPOtemperature=1.0, sampling=average@32, multi-turn=true2026.0342.13
Seq-MIStemperature=1.0, sampling=average@32, multi-turn=true2026.0342.05
Token-MIStemperature=1.0, sampling=average@32, multi-turn=true2026.0341.45
Seq-Bypasstemperature=1.0, sampling=average@32, multi-turn=true2026.0339.21