List your company

Mathematical Reasoning on AIME 25 (Acc@8)

30.83Acc@8GRPO-DBB
3.5310.617517.70524.7925Mar 19, 2026

Evaluation results

MethodLinks
GRPO-DBBBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0330.83
GRPOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0326.67
RePOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0322.92
GRPO-DBBBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.037.08
RePOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.036.67
GRPOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.034.58