General Reasoning on BBH (Acc@8)
63.32Acc@8GRPO-DBB
Evaluation Results
| Method | Links | |
|---|---|---|
| GRPO-DBBBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.03 | 63.32 | |
| GRPOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.03 | 59.18 | |
| RePOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.03 | 42.96 | |
| GRPO-DBBBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.03 | 33.97 | |
| RePOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.03 | 30.95 | |
| GRPOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.03 | 12.71 |