Mathematical Reasoning on Omni-Math (Avg@8)
25.34Average Score @8IntroLLM
Evaluation Results
| Method | Links | |
|---|---|---|
| IntroLLMBackbone=Qwen3-4B-Base2026.02 | 25.34 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.22026.02 | 24.35 | |
| EADBackbone=Qwen3-4B-Base, Schedule=1.2→0.12026.02 | 24.32 | |
| TAMPOBackbone=Qwen3-4B-Base, Range=0.6-1.52026.02 | 23.92 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=1.02026.02 | 23.88 | |
| GRPOBackbone=Qwen3-4B-Base, Temperature (τ)=0.62026.02 | 23.41 | |
| IntroLLMBackbone=Qwen3-1.7B-Base2026.02 | 18.43 | |
| EADBackbone=Qwen3-1.7B-Base, Schedule=1.2→0.12026.02 | 17.9 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.22026.02 | 17.43 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=1.02026.02 | 17.4 | |
| TAMPOBackbone=Qwen3-1.7B-Base, Range=0.6-1.52026.02 | 17.28 | |
| GRPOBackbone=Qwen3-1.7B-Base, Temperature (τ)=0.62026.02 | 16.66 | |
| BaseBackbone=Qwen3-4B-Base2026.02 | 14.94 | |
| BaseBackbone=Qwen3-1.7B-Base2026.02 | 8.23 |