Mathematical Reasoning on Minerva Math (Avg@8)
23.9Avg@8EAD
Evaluation Results
| Method | Links | |
|---|---|---|
| EADBackbone=Qwen3-4B-Base, Schedule=1.2→0.12026.02 | 23.9 | |
| IntroLLMBackbone=Qwen3-4B-Base2026.02 | 23.48 | |
| TAMPOBackbone=Qwen3-4B-Base, Range=0.6-1.52026.02 | 22.79 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.22026.02 | 22.61 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.02026.02 | 21.51 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=0.62026.02 | 21.09 | |
| IntroLLMBackbone=Qwen3-1.7B-Base2026.02 | 18.29 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.22026.02 | 17.33 | |
| EADBackbone=Qwen3-1.7B-Base, Schedule=1.2→0.12026.02 | 17.33 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.02026.02 | 17.28 | |
| TAMPOBackbone=Qwen3-1.7B-Base, Range=0.6-1.52026.02 | 16.64 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=0.62026.02 | 15.17 | |
| BaseBackbone=Qwen3-4B-Base2026.02 | 12.5 | |
| BaseBackbone=Qwen3-1.7B-Base2026.02 | 7.12 |