List your company

Mathematical Reasoning on AMC 2023 (Accuracy (avg@32), Average)

94.77Accuracy (avg@32)SRaR
50.486861.983473.4884.9766Mar 10, 2026Mar 26, 2026Apr 11, 2026Apr 27, 2026May 13, 2026May 29, 2026Jun 15, 2026

Evaluation results

MethodLinks
SRaRModel Size=32B2026.0594.77—
RaRModel Size=32B2026.0594.22—
DS-R1-Distill-Qwen-7B + IC-DAPOBackbone=Qwen-7B, Zero-shot mode=true, Time/Step (s)=315.62026.0393.767.8
DAPOModel Size=32B2026.0593.67—
DS-R1-Distill-Qwen-7B + CE-GPPOBackbone=Qwen-7B, Zero-shot mode=true, Time/Step (s)=292.52026.0393.367.3
SRaRModel Size=8B2026.0592.73—
DS-R1-Distill-Qwen-7B + DAPOBackbone=Qwen-7B, Zero-shot mode=true, Time/Step (s)=303.12026.0392.365.3
DS-R1-Distill-Qwen-7BBackbone=Qwen-7B, Zero-shot mode=true2026.0390.661.8
DAPOModel Size=8B2026.0590.23—
DS-R1-Distill-Qwen-7B + GRPOBackbone=Qwen-7B, Zero-shot mode=true, Time/Step (s)=305.62026.0388.861.4
RaRModel Size=8B2026.0588.2—
RGR-GRPOModel Size=32B2026.0587.42—
DS-R1-Distill-Qwen-1.5B + IC-DAPOBackbone=Qwen-1.5B, Zero-shot mode=true, Time/Step (s)=477.22026.0386.256.4
DS-R1-Distill-Qwen-1.5B + GSPOBackbone=Qwen-1.5B, Zero-shot mode=true, Time/Step (s)=437.32026.0385.955.7
DS-R1-Distill-Qwen-1.5B + CE-GPPOBackbone=Qwen-1.5B, Zero-shot mode=true, Time/Step (s)=464.02026.0385.855.7
DS-R1-Distill-Qwen-1.5B + DAPOBackbone=Qwen-1.5B, Zero-shot mode=true, Time/Step (s)=459.62026.0384.453.9
GRPO-VPSModel Size=8B2026.0583.2—
RGR-GRPOModel Size=8B2026.0581.09—
DS-R1-Distill-Qwen-1.5B + CISPOBackbone=Qwen-1.5B, Zero-shot mode=true, Time/Step (s)=466.32026.0380.948.8
GRPOModel Size=32B2026.0580.78—
GRPO-VPSModel Size=32B2026.0580.08—
DS-R1-Distill-Qwen-1.5B + GRPOBackbone=Qwen-1.5B, Zero-shot mode=true, Time/Step (s)=457.42026.0379.350.3
GRPOModel Size=8B2026.0579.06—
DS-R1-Distill-Qwen-1.5BBackbone=Qwen-1.5B, Zero-shot mode=true2026.0373.746.3
BaselineModel Size=8B2026.0572.03—
BaselineModel Size=32B2026.0571.48—
GRPOModel=Qwen2.5-Math-7B, G=162026.0668.91—
RF++ w/ NTFModel=Qwen2.5-Math-7B, G=12026.0668.91—
GRPOModel=Qwen2.5-Math-7B, G=22026.0664.84—
C-RF w/ NTFModel=Qwen2.5-Math-7B, G=12026.0661.95—
RF++Model=Qwen2.5-Math-7B, G=82026.0658.36—
GRPOModel=Qwen2.5-Math-1.5B, G=162026.0657.11—
RF++ w/ NTFModel=Qwen2.5-Math-1.5B, G=12026.0655.47—
C-RF w/ NTFModel=Qwen2.5-Math-1.5B, G=12026.0655.47—
RF++Model=Qwen2.5-Math-1.5B, G=82026.0654.77—
GRPOModel=Qwen2.5-Math-1.5B, G=22026.0652.19—