#ModelAccuracyPaper
1PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning90.90link
2+ GRPO-Ξ»74.40link
3Vanilla74.10link
4+GRPO72.70link
5+LP71.90link
6Weak-to-Strong Generalization via Direct On-Policy Distillation58.30link