List your company

Mathematical Reasoning on Omni-Math (Avg@8)

25.34Average Score @8IntroLLM
7.545612.165316.78521.4047Feb 13, 2026

Evaluation results

MethodLinks
IntroLLMBackbone=Qwen3-4B-Base2026.0225.34
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.22026.0224.35
EADBackbone=Qwen3-4B-Base, Schedule=1.2→0.12026.0224.32
TAMPOBackbone=Qwen3-4B-Base, Range=0.6-1.52026.0223.92
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.02026.0223.88
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=0.62026.0223.41
IntroLLMBackbone=Qwen3-1.7B-Base2026.0218.43
EADBackbone=Qwen3-1.7B-Base, Schedule=1.2→0.12026.0217.9
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.22026.0217.43
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.02026.0217.4
TAMPOBackbone=Qwen3-1.7B-Base, Range=0.6-1.52026.0217.28
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=0.62026.0216.66
BaseBackbone=Qwen3-4B-Base2026.0214.94
BaseBackbone=Qwen3-1.7B-Base2026.028.23