Self-Play Search Distillation for Large Language Model Reasoning
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-math-500
SPSD-Qwen3-4B-Base (OPSD)
–
Accuracy: 46.8
mathematical-reasoning-on-minerva-math
SPSD-Qwen3-4B-Base (OPSD)
–
Accuracy: 21.7
Rank counts only results with a code link.