Mathematical Reasoning on AIME 2026 (mean@30, pass@30)
27.6Mean Score @30IWM & RL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| IWM & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL2026.06 | 27.6 | 56.7 | |
| FE-SFT & FC-RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.06 | 27.1 | 60 | |
| State-SFT & RL†Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.06 | 27 | 60 | |
| FE-SFT & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.06 | 26 | 50 | |
| SFT & RLBackbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.06 | 25.9 | 53.3 | |
| FE-SFT & RL*Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.06 | 25.7 | 46.7 | |
| State-SFT & RL‡Backbone=Youtu-LLM-2B-Base, Training Stage=RL, Framework=WM-AMT2026.06 | 25 | 50 | |
| SFT & RL*Backbone=Youtu-LLM-2B-Base, Training Stage=RL2026.06 | 24.6 | 53.3 |