List your company
ResearchFormerly WizWand

Mathematical Reasoning on GAO23

56.62Pass@1+CurES-GRPO
23.932832.418940.90549.3911Oct 1, 2025
Updated 7mo ago

Evaluation results

MethodLinks
+CurES-GRPOBase Model=Qwen2.5-Math-7B, Training Method=CurES-GRPO2025.1056.6252.41
+RPPBase Model=Qwen2.5-Math-7B, Training Method=RPP2025.1055.5850.18
+Speed-RL-GRPOBase Model=Qwen2.5-Math-7B, Training Method=Speed-RL-GRPO2025.1055.5848.84
+GVM-RPPBase Model=Qwen2.5-Math-7B, Training Method=GVM-RPP2025.1055.3246.95
+CurES-RPPBase Model=Qwen2.5-Math-7B, Training Method=CurES-RPP2025.1054.5549.62
+GVM-GRPOBase Model=Qwen2.5-Math-7B, Training Method=GVM-GRPO2025.1054.0350.64
+Speed-RL-RPPBase Model=Qwen2.5-Math-7B, Training Method=Speed-RL-RPP2025.1053.7749.56
+CurES-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=CurES-GRPO2025.1051.4344.94
+CurES-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=CurES-RPP2025.1051.4344.14
+GRPOBase Model=Qwen2.5-Math-7B, Training Method=GRPO2025.1051.4347.59
Qwen2.5-Math-1.5B + CurES-GRPOBackbone=Qwen2.5-Math-1.5B, Training Method=CurES-GRPO2025.1051.43—
Qwen2.5-Math-1.5B + MoPPSBackbone=Qwen2.5-Math-1.5B, Training Method=MoPPS2025.1050.25—
+GVM-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=GVM-RPP2025.1049.6142.21
Qwen2.5-Math-1.5B + DAPOBackbone=Qwen2.5-Math-1.5B, Training Method=DAPO2025.1049.61—
+GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=GRPO2025.1048.8341.64
+GVM-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=GVM-GRPO2025.1048.8342.82
+Speed-RL-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=Speed-RL-RPP2025.1048.3141.75
+Speed-RL-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=Speed-RL-GRPO2025.1047.1441.34
Qwen2.5-Math-7BBase Model=Qwen2.5-Math-7B, Training Method=Base2025.1044.6833.48
+RPPBase Model=Qwen2.5-Math-1.5B, Training Method=RPP2025.1042.0835.86
Qwen2.5-Math-1.5BBase Model=Qwen2.5-Math-1.5B, Training Method=Base2025.1025.1920
Qwen2.5-Math-1.5BBackbone=Qwen2.5-Math-1.5B, Training Method=Base2025.1025.19—