List your company

Software Engineering on SWE tasks Performance Data n = 10 (test)

49.64F1 ScoreIn-Context
42.380844.265446.1548.0346Jun 29, 2026

Evaluation results

MethodLinks
In-ContextBackbone=Qwen3-8B, Skill Type=In-context skills2026.0649.6487.5833
No-SkillBackbone=Qwen3-8B, Skill Type=None2026.0648.9887.3937
ParametricSkillsBackbone=Qwen3-8B, Skill Type=Parametric (Hypernetwork generated)2026.0644.8988.1238.5
SHINEBackbone=Qwen3-8B, Skill Type=Parametric (SHINE checkpoint)2026.0642.6686.3625