List your company

Mathematical Reasoning on AIME 2024 (mean@30, pass@30)

35.1Mean @30SFT & RL*
31.77232.63633.534.364Jun 25, 2026

Evaluation results

MethodLinks
SFT & RL*Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0635.156.7
FE-SFT & FC-RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0634.666.7
SFT & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0634.263.3
FE-SFT & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0633.660
IWM & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0633.266.7
State-SFT & RL‡Backbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0633.263.3
State-SFT & RL†Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0632.260
FE-SFT & RL*Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0631.960