List your company

Reward Maximization on SHP

0.53Win RateAISP
0.270.33750.4050.4725Oct 30, 2025

Evaluation results

MethodLinks
AISPBase Model=Gemma3 4B, Reward Model=UltraRM2025.100.53
AISPBase Model=Gemma3 4B, Reward Model=Eurus2025.100.527
AISPBase Model=Llama3 8B, Reward Model=UltraRM2025.100.513
AISPBase Model=Llama3 8B, Reward Model=Eurus2025.100.47
BoN (top-p)Base Model=Llama3 8B, Reward Model=Eurus2025.100.453
BoN (top-p)Base Model=Llama3 8B, Reward Model=UltraRM2025.100.42
BoN (top-p)Base Model=Gemma3 4B, Reward Model=UltraRM2025.100.413
BoN (top-p)Base Model=Gemma3 4B, Reward Model=Eurus2025.100.39
AISPBase Model=Vicuna 7B, Reward Model=Eurus2025.100.36
AISPBase Model=Vicuna 7B, Reward Model=UltraRM2025.100.353
BoN (top-p)Base Model=Vicuna 7B, Reward Model=UltraRM2025.100.343
BoN (top-p)Base Model=Vicuna 7B, Reward Model=Eurus2025.100.28