List your company

Mathematical Reasoning on AIME24 (Pass@1, #Tk)

33.33Pass@1DRP
-1.33327.665916.66525.6641Jan 26, 2026

Evaluation results

MethodLinks
DRPBackbone=Phi-4-Reasoning2026.0133.336,135
TALEBackbone=Phi-4-Reasoning2026.01292,069.97
FROSTBackbone=Phi-4-Reasoning2026.0126.67899.8
DRPBackbone=GPT-oss-20B2026.0122.454,983
TALEBackbone=GPT-oss-20B2026.01201,354.67
FROSTBackbone=GPT-oss-20B2026.0116.671,009.6
ThinkLessBackbone=Phi-4-Reasoning2026.0116.081,405.4
ThinkLessBackbone=GPT-oss-20B2026.01161,205
SelfBudgeterBackbone=Phi-4-Reasoning2026.0113.421,372.83
BaseBackbone=GPT-oss-20B2026.0113.331,003.57
SelfBudgeterBackbone=GPT-oss-20B2026.0113.21,256
FROSTBackbone=Magistral-Small-1.12026.019.74149.93
BaseBackbone=Phi-4-Reasoning2026.016.671,017.7
ThinkLessBackbone=Magistral-Small-1.12026.0161,205
SelfBudgeterBackbone=Magistral-Small-1.12026.015.21,256
DRPBackbone=Magistral-Small-1.12026.014.51,350.77
TALEBackbone=Magistral-Small-1.12026.013.33967.43
BaseBackbone=Magistral-Small-1.12026.010537.13