List your company

Mathematical Reasoning on AIME 25 (avg@8)

53.8Avg@8 ScoreNPR (Variant)
8.66420.38232.143.818Dec 8, 2025

Evaluation results

MethodLinks
NPR (Variant)Data=orz-8k, Train=Parallel RL, Base=NPR-BETA2025.1253.8
NPRData=orz-8k, Train=Parallel RL, Base=NPR-BETA2025.1250.4
SRData=orz-8k, Train=Sequential RL, Base=NPR-BETA2025.1249.2
Qwen3-4B-Instruct-2507Data=N/A, Train=N/A, Base=N/A2025.1247.4
Multiverse-32BData=s1.1-8k, Train=S→P SFT, Base=Q2.5-32B-Inst.2025.1245.8
NPR-BETA (Variant)Data=orz-8k, Train=Parallel SFT, Base=Q3-4B2025.1243.8
Multiverse-4BData=s1.1-8k, Train=S→P SFT, Base=Q3-4B-Inst.2025.1242.9
NPR-BETAData=orz-8k, Train=Parallel SFT, Base=Q3-4B-Inst.2025.1242.9
SR-BETAData=orz-8k, Train=Sequential SFT, Base=Q3-4B-Inst.2025.1237.1
Qwen3-4B (Non-Thinking)Data=N/A, Train=N/A, Base=N/A2025.1219.1
Qwen2.5-32B-InstructData=N/A, Train=N/A, Base=N/A2025.1210.4