List your company

Software Engineering on SWE-rebench 9B

38.16Avg@8 BC%EvoTrainer
29.871232.023134.17536.3269Jun 2, 2026

Evaluation results

MethodLinks
EvoTrainerConfiguration=Proposed Method2026.0638.16
RAGEN v2 SNR FilteringConfiguration=Algorithmic Baseline2026.0635.74
Human-engineered RLConfiguration=Reference2026.0633.77
AutoResearchConfiguration=Reference2026.0633.33
RAGEN v1 FilteringConfiguration=Algorithmic Baseline2026.0632.89
GRPO + Clip-HigherConfiguration=Algorithmic Baseline2026.0632.79
Group-Variance FilteringConfiguration=Algorithmic Baseline2026.0632.31
GSPO + Clip-HigherConfiguration=Algorithmic Baseline2026.0631.97
Base model (no RL)RL=None2026.0630.19