List your company

Mathematical Reasoning on AIME25 (pass@1 (%))

66.67Pass@1PREPO
-1.366816.296633.9651.6234Nov 2, 2025

Evaluation results

MethodLinks
PREPOBase Model=Qwen3-4B, Training Strategy=PREPO, # Rollouts=348K2025.1166.67
Random SelectionBase Model=Qwen3-4B, Training Strategy=Random Selection, # Rollouts=553K2025.1160
GRESOBase Model=Qwen3-4B, Training Strategy=GRESO, # Rollouts=472K2025.1156.67
Qwen3-4BBase Model=Qwen3-4B, Training Strategy=Base, # Rollouts=–2025.1130
Random SelectionBase Model=Qwen2.5-Math-1.5B, Training Strategy=Random Selection, # Rollouts=3.0M2025.1120
PREPOBase Model=Qwen2.5-Math-1.5B, Training Strategy=PREPO, # Rollouts=1.1M2025.1120
GRESOBase Model=Qwen2.5-Math-7B, Training Strategy=GRESO, # Rollouts=654K2025.1118.33
GRESOBase Model=Qwen2.5-Math-1.5B, Training Strategy=GRESO, # Rollouts=2.5M2025.1115.38
PREPOBase Model=Qwen2.5-Math-7B, Training Strategy=PREPO, # Rollouts=540K2025.1112.81
PREPOBase Model=Qwen2.5-7B, Training Strategy=PREPO, # Rollouts=304K2025.1110.21
Random SelectionBase Model=Qwen2.5-Math-7B, Training Strategy=Random Selection, # Rollouts=905K2025.1110
GRESOBase Model=Qwen2.5-7B, Training Strategy=GRESO, # Rollouts=680K2025.119.22
Qwen2.5-Math-7BBase Model=Qwen2.5-Math-7B, Training Strategy=Base, # Rollouts=–2025.119.17
Random SelectionBase Model=Qwen2.5-7B, Training Strategy=Random Selection, # Rollouts=716K2025.116.98
Qwen2.5-Math-1.5BBase Model=Qwen2.5-Math-1.5B, Training Strategy=Base, # Rollouts=–2025.113.54
Qwen2.5-7BBase Model=Qwen2.5-7B, Training Strategy=Base, # Rollouts=–2025.111.25