Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime-2025
N-OPSD (Qwen3-8B)
–
Accuracy: 72.78
mathematical-reasoning-on-aime24
N-OPSD (Qwen3-8B)
–
Acc: 78.7
mathematical-reasoning-on-hmmt-feb-2025
N-OPSD (Qwen3-8B)
–
Accuracy: 48.24
Rank counts only results with a code link.