List your company

Mathematical Reasoning on AIME 24 (P@1, P@4)

10.83P@1ICT
-0.43322.49095.4158.3391Jun 18, 2026

Evaluation results

MethodLinks
ICTModel Size=Qwen2.5-7B2026.0610.8323.33
BaseModel Size=Qwen2.5-7B2026.061020
STAPOModel Size=Qwen2.5-7B2026.061020
20-EntropyModel Size=Qwen2.5-7B2026.066.6713.33
GRPOModel Size=Qwen2.5-7B2026.06516.67
ICTModel Size=Qwen2.5-1.5B2026.062.8413.64
STAPOModel Size=Qwen2.5-1.5B2026.061.714.55
BaseModel Size=Qwen2.5-1.5B2026.061.426.82
STAPOModel Size=Qwen2.5-0.5B2026.060.572.27
ICTModel Size=Qwen2.5-0.5B2026.060.572.27
20-EntropyModel Size=Qwen2.5-1.5B2026.060.572.27
GRPOModel Size=Qwen2.5-0.5B2026.060.562.25
GRPOModel Size=Qwen2.5-1.5B2026.060.284.56
BaseModel Size=Qwen2.5-0.5B2026.0600
20-EntropyModel Size=Qwen2.5-0.5B2026.0600