List your company

General Reasoning on BBH (Acc@8)

63.32Acc@8GRPO-DBB
10.685624.350338.01551.6797Mar 19, 2026

Evaluation results

MethodLinks
GRPO-DBBBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0363.32
GRPOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0359.18
RePOBackbone=Qwen3-8B-Base, Training Dataset=DAPO-Math-17k2026.0342.96
GRPO-DBBBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.0333.97
RePOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.0330.95
GRPOBackbone=Qwen3-1.7B-Base, Training Dataset=DAPO-Math-17k2026.0312.71