List your company

Mathematical Reasoning on AMC24 (Acc@8)

60Acc@8GRPO-DBB
20.136830.485940.83551.1841Mar 19, 2026

Evaluation results

MethodLinks
GRPO-DBBBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0360
GRPOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0356.39
RePOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0356.11
GRPO-DBBBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.0326.94
GRPOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.0323.61
RePOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.0321.67