List your company

Mathematical Reasoning on MATH 500 (Avg@8, Pass@8)

80.73Avg@8 ScoreIntroLLM
29.322842.668956.01569.3611Feb 13, 2026

Evaluation results

MethodLinks
IntroLLMBackbone=Qwen3-4B-Base2026.0280.7393
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.22026.0280.0392
EADBackbone=Qwen3-4B-Base, Schedule=1.2→0.12026.028092.2
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.02026.0279.192
TAMPOBackbone=Qwen3-4B-Base, Range=0.6-1.52026.0278.2391.8
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=0.62026.0277.691.4
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.22026.0268.3585.4
IntroLLMBackbone=Qwen3-1.7B-Base2026.0267.5386.2
EADBackbone=Qwen3-1.7B-Base, Schedule=1.2→0.12026.0267.0385.8
TAMPOBackbone=Qwen3-1.7B-Base, Range=0.6-1.52026.0265.4584.8
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.02026.0265.2584
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=0.62026.0264.685.6
BaseBackbone=Qwen3-4B-Base2026.0248.6886.4
BaseBackbone=Qwen3-1.7B-Base2026.0231.374.8