List your company

Mathematical Reasoning on GSM8K (Pass@1, Avg.)

92.27Pass@1+CurES-GRPO
41.965255.025168.08581.1449Oct 1, 2025

Evaluation results

MethodLinks
+CurES-GRPOBase Model=Qwen2.5-Math-7B, Training Method=CurES-GRPO2025.1092.2752.41
+RPPBase Model=Qwen2.5-Math-7B, Training Method=RPP2025.1091.8950.18
+CurES-RPPBase Model=Qwen2.5-Math-7B, Training Method=CurES-RPP2025.1091.8949.62
+Speed-RL-RPPBase Model=Qwen2.5-Math-7B, Training Method=Speed-RL-RPP2025.1091.8149.56
+GRPOBase Model=Qwen2.5-Math-7B, Training Method=GRPO2025.1091.4347.59
+GVM-GRPOBase Model=Qwen2.5-Math-7B, Training Method=GVM-GRPO2025.1091.2850.64
+GVM-RPPBase Model=Qwen2.5-Math-7B, Training Method=GVM-RPP2025.1090.0746.95
+Speed-RL-GRPOBase Model=Qwen2.5-Math-7B, Training Method=Speed-RL-GRPO2025.1088.748.84
+GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=GRPO2025.1086.4341.64
+CurES-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=CurES-GRPO2025.1085.9744.94
+CurES-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=CurES-RPP2025.1085.8244.14
+Speed-RL-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=Speed-RL-GRPO2025.1085.6741.34
+Speed-RL-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=Speed-RL-RPP2025.1085.6741.75
+GVM-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=GVM-GRPO2025.1084.2342.82
+GVM-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=GVM-RPP2025.108442.21
+RPPBase Model=Qwen2.5-Math-1.5B, Training Method=RPP2025.1082.9435.86
Qwen2.5-Math-7BBase Model=Qwen2.5-Math-7B, Training Method=Base2025.1072.433.48
Qwen2.5-Math-1.5BBase Model=Qwen2.5-Math-1.5B, Training Method=Base2025.1043.920