List your company

Mathematical Reasoning on AIME 24 (Avg@8, Pass@8)

19.17Avg@8IntroLLM
0.975.69510.4215.145Feb 13, 2026

Evaluation results

MethodLinks
IntroLLMBackbone=Qwen3-4B-Base2026.0219.1740
TAMPOBackbone=Qwen3-4B-Base, Range=0.6-1.52026.021533.33
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.22026.0214.5830
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.02026.0214.1733.33
EADBackbone=Qwen3-4B-Base, Schedule=1.2→0.12026.0214.1736.67
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=0.62026.0211.6730
IntroLLMBackbone=Qwen3-1.7B-Base2026.029.5826.67
TAMPOBackbone=Qwen3-1.7B-Base, Range=0.6-1.52026.027.9223.33
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.22026.027.523.33
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.02026.027.0816.67
EADBackbone=Qwen3-1.7B-Base, Schedule=1.2→0.12026.027.0823.33
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=0.62026.026.6720
BaseBackbone=Qwen3-4B-Base2026.026.6720
BaseBackbone=Qwen3-1.7B-Base2026.021.6710