Mathematical Reasoning on AMC24 (Acc@8)
60Acc@8GRPO-DBB
Evaluation Results
| Method | Links | |
|---|---|---|
| GRPO-DBBBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.03 | 60 | |
| GRPOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.03 | 56.39 | |
| RePOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.03 | 56.11 | |
| GRPO-DBBBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.03 | 26.94 | |
| GRPOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.03 | 23.61 | |
| RePOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.03 | 21.67 |