List your company
ResearchFormerly WizWand

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

43.56Pass@1+CurES-GRPO
20.139226.219632.338.3804Oct 1, 2025
Updated 7mo ago

Evaluation results

MethodLinks
+CurES-GRPOBase Model=Qwen2.5-Math-7B, Training Method=CurES-GRPO2025.1043.5652.41
+Speed-RL-RPPBase Model=Qwen2.5-Math-7B, Training Method=Speed-RL-RPP2025.1042.9649.56
+GVM-GRPOBase Model=Qwen2.5-Math-7B, Training Method=GVM-GRPO2025.1042.6750.64
+Speed-RL-GRPOBase Model=Qwen2.5-Math-7B, Training Method=Speed-RL-GRPO2025.1042.3748.84
+CurES-RPPBase Model=Qwen2.5-Math-7B, Training Method=CurES-RPP2025.1040.5949.62
+GVM-RPPBase Model=Qwen2.5-Math-7B, Training Method=GVM-RPP2025.1040.346.95
+RPPBase Model=Qwen2.5-Math-7B, Training Method=RPP2025.104050.18
+GRPOBase Model=Qwen2.5-Math-7B, Training Method=GRPO2025.1038.3747.59
+CurES-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=CurES-GRPO2025.1037.3344.94
Qwen2.5-Math-1.5B + MoPPSBackbone=Qwen2.5-Math-1.5B, Training Method=MoPPS2025.1037.33—
Qwen2.5-Math-1.5B + CurES-GRPOBackbone=Qwen2.5-Math-1.5B, Training Method=CurES-GRPO2025.1037.33—
+CurES-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=CurES-RPP2025.1037.0444.14
+Speed-RL-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=Speed-RL-RPP2025.1036.341.75
+Speed-RL-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=Speed-RL-GRPO2025.1035.5641.34
+GVM-GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=GVM-GRPO2025.1035.5642.82
+GVM-RPPBase Model=Qwen2.5-Math-1.5B, Training Method=GVM-RPP2025.1035.5642.21
+GRPOBase Model=Qwen2.5-Math-1.5B, Training Method=GRPO2025.1035.4141.64
Qwen2.5-Math-1.5B + DAPOBackbone=Qwen2.5-Math-1.5B, Training Method=DAPO2025.1035.26—
Qwen2.5-Math-7BBase Model=Qwen2.5-Math-7B, Training Method=Base2025.1030.8133.48
+RPPBase Model=Qwen2.5-Math-1.5B, Training Method=RPP2025.1029.1935.86
Qwen2.5-Math-1.5BBase Model=Qwen2.5-Math-1.5B, Training Method=Base2025.1021.0420
Qwen2.5-Math-1.5BBackbone=Qwen2.5-Math-1.5B, Training Method=Base2025.1021.04—