List your company

Mathematical Reasoning on AMC 23 (Avg@8, Pass@8)

52.5Avg@8IntroLLM
16.744826.027435.3144.5926Feb 13, 2026

Evaluation results

MethodLinks
IntroLLMBackbone=Qwen3-4B-Base2026.0252.587.5
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.22026.0251.8882.5
EADBackbone=Qwen3-4B-Base, Schedule=1.2→0.12026.0251.8877.5
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=0.62026.0250.9482.5
TAMPOBackbone=Qwen3-4B-Base, Range=0.6-1.52026.0250.6282.5
GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.02026.025080
IntroLLMBackbone=Qwen3-1.7B-Base2026.0239.0672.5
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.02026.0237.567.5
EADBackbone=Qwen3-1.7B-Base, Schedule=1.2→0.12026.0237.570
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.22026.0235.6370
GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=0.62026.023567.5
TAMPOBackbone=Qwen3-1.7B-Base, Range=0.6-1.52026.023570
BaseBackbone=Qwen3-4B-Base2026.0227.1972.5
BaseBackbone=Qwen3-1.7B-Base2026.0218.1265