List your company

Mathematical Reasoning on AIME 2025 (mean@30, pass@30)

26.8Mean Score @30FE-SFT & FC-RL
21.91223.18124.4525.719Jun 25, 2026

Evaluation results

MethodLinks
FE-SFT & FC-RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0626.853.3
FE-SFT & RL*Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0626.446.7
FE-SFT & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0625.653.3
IWM & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0624.950
State-SFT & RL‡Backbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0624.856.7
SFT & RL*Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0624.346.7
SFT & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.0623.453.3
State-SFT & RL†Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.0622.150