List your company

Mathematical Reasoning on Math500 (P@1, P@4)

82.25Pass@1ICT
7.349226.794646.2465.6854Jun 18, 2026

Evaluation results

MethodLinks
ICTModel Size=Qwen2.5-7B2026.0682.2595.2
STAPOModel Size=Qwen2.5-7B2026.0678.0593.6
20-EntropyModel Size=Qwen2.5-7B2026.0673.393.2
GRPOModel Size=Qwen2.5-7B2026.0673.2593.2
BaseModel Size=Qwen2.5-7B2026.0672.5592.4
ICTModel Size=Qwen2.5-1.5B2026.0623.5537.6
STAPOModel Size=Qwen2.5-1.5B2026.0618.0532.8
20-EntropyModel Size=Qwen2.5-1.5B2026.0617.9531.6
GRPOModel Size=Qwen2.5-1.5B2026.0617.933.8
BaseModel Size=Qwen2.5-1.5B2026.0617.2531.4
ICTModel Size=Qwen2.5-0.5B2026.0612.1524.8
GRPOModel Size=Qwen2.5-0.5B2026.0611.723.2
20-EntropyModel Size=Qwen2.5-0.5B2026.0611.3522.4
BaseModel Size=Qwen2.5-0.5B2026.0611.0521.2
STAPOModel Size=Qwen2.5-0.5B2026.0610.2321.5