Mathematical Reasoning on MATH 500 (Avg@8, Pass@8)
80.73Avg@8 ScoreIntroLLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| IntroLLMBackbone=Qwen3-4B-Base2026.02 | 80.73 | 93 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.22026.02 | 80.03 | 92 | |
| EADBackbone=Qwen3-4B-Base, Schedule=1.2→0.12026.02 | 80 | 92.2 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.02026.02 | 79.1 | 92 | |
| TAMPOBackbone=Qwen3-4B-Base, Range=0.6-1.52026.02 | 78.23 | 91.8 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=0.62026.02 | 77.6 | 91.4 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.22026.02 | 68.35 | 85.4 | |
| IntroLLMBackbone=Qwen3-1.7B-Base2026.02 | 67.53 | 86.2 | |
| EADBackbone=Qwen3-1.7B-Base, Schedule=1.2→0.12026.02 | 67.03 | 85.8 | |
| TAMPOBackbone=Qwen3-1.7B-Base, Range=0.6-1.52026.02 | 65.45 | 84.8 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.02026.02 | 65.25 | 84 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=0.62026.02 | 64.6 | 85.6 | |
| BaseBackbone=Qwen3-4B-Base2026.02 | 48.68 | 86.4 | |
| BaseBackbone=Qwen3-1.7B-Base2026.02 | 31.3 | 74.8 |