List your company

Mathematical Reasoning on MinervaMath (test)

47.79Pass@1GRPO
8.415618.637828.8639.0822May 26, 2025

Evaluation results

MethodLinks
GRPOStudent=Qwen2.5 14B2025.0547.79—
Qwen2.5-14B (R)Role=Standalone Teacher2025.0547.79—
GRPOStudent=Qwen2.5 32B2025.0546.69—
W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-14B (R)2025.0545.59200
W2SR-PStudent=Qwen2.5 14B, Teacher=Qwen2.5-7B (R)2025.0545.2270.86
W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-14B (R)2025.0544.85267.27
W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-7B (R)2025.0542.2842.88
W2SRStudent=Qwen2.5 14B, Teacher=Qwen2.5-7B (R)2025.0541.5429.14
W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-7B (R)2025.0540.8123.83
W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-1.5B (R)2025.0540.0773.91
W2SR-PStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-1.5B (R)2025.0539.71108.69
Qwen2.5-7B (R)Role=Standalone Teacher2025.0538.97—
GRPOStudent=Qwen2.5 Math-7B2025.0538.24—
W2SR-PStudent=Qwen2.5 14B, Teacher=Qwen2.5-1.5B (R)2025.0538.2463.92
W2SRStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-1.5B (R)2025.0537.595.63
W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-1.5B (R)2025.0537.1362.32
W2SR-PStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-0.5B (R)2025.0536.493.5
W2SRStudent=Qwen2.5 14B, Teacher=Qwen2.5-1.5B (R)2025.0532.7243.07
LIMOStudent=Qwen2.5 14B2025.0531.25—
LIMOStudent=Qwen2.5 Math-7B2025.0530.88—
LIMOStudent=Qwen2.5 32B2025.0530.51—
VanillaStudent=Qwen2.5 32B2025.0529.04—
VanillaStudent=Qwen2.5 14B2025.0528.31—
W2SRStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-0.5B (R)2025.0526.8459.73
Qwen2.5-1.5B (R)Role=Standalone Teacher2025.0521.32—
VanillaStudent=Qwen2.5 Math-7B2025.0513.6—
Qwen2.5-0.5B (R)Role=Standalone Teacher2025.059.93—