List your company

Machine Translation on Challenge ZH-EN

17.16BLEUPEGRL
15.454415.897216.3416.7828Feb 3, 2026

Evaluation results

MethodLinks
PEGRLBackbone=Qwen3-0.6B, RL training=PEGRL, Rollouts per example=722026.0217.1662.3464.63
MT-R1-ZeroBackbone=Qwen3-0.6B, RL training=MT-R1-Zero, Rollouts per example=722026.0216.8861.5663.41
Qwen3-0.6BTraining=Pre-trained only2026.0215.5258.8362.91