List your company

Mathematical Reasoning on MATH500 (avg@1)

93.6Average Score (avg@1)NPR
79.87283.4368790.564Dec 8, 2025

Evaluation results

MethodLinks
NPRData=orz-8k, Train=Parallel RL, Base=NPR-BETA2025.1293.6
Qwen3-4B-Instruct-2507Data=N/A, Train=N/A, Base=N/A2025.1293.4
SRData=orz-8k, Train=Sequential RL, Base=NPR-BETA2025.1292.8
SR-BETAData=orz-8k, Train=Sequential SFT, Base=Q3-4B-Inst.2025.1292
Multiverse-32BData=s1.1-8k, Train=S→P SFT, Base=Q2.5-32B-Inst.2025.1291.8
NPR (Variant)Data=orz-8k, Train=Parallel RL, Base=NPR-BETA2025.1291.8
NPR-BETAData=orz-8k, Train=Parallel SFT, Base=Q3-4B-Inst.2025.1291.6
NPR-BETA (Variant)Data=orz-8k, Train=Parallel SFT, Base=Q3-4B2025.1286.8
Qwen3-4B (Non-Thinking)Data=N/A, Train=N/A, Base=N/A2025.1284.8
Multiverse-4BData=s1.1-8k, Train=S→P SFT, Base=Q3-4B-Inst.2025.1281.6
Qwen2.5-32B-InstructData=N/A, Train=N/A, Base=N/A2025.1280.4