List your company

Mathematical Reasoning on AMC 23 (Pass@1, #Tokens)

92.5Pass@1CREST
53.563.62573.7583.875Dec 31, 2025

Evaluation results

MethodLinks
CRESTModel=R1-7B2025.1292.53,937
CRESTModel=R1-1.5B2025.12905,584
TIPModel=R1-7B2025.12905,532
VanillaModel=R1-7B2025.1287.55,912
SEALModel=R1-7B2025.1287.54,784
Soft-ThinkingModel=R1-7B2025.12805,859
DynasorModel=R1-7B2025.12757,809
VanillaModel=R1-1.5B2025.1272.58,951
TIPModel=R1-1.5B2025.1272.58,069
DynasorModel=R1-1.5B2025.12707,782
SEALModel=R1-1.5B2025.1267.58,202
Soft-ThinkingModel=R1-1.5B2025.125513,160