Software Engineering Skill Evaluation on SWE-Skills-Bench python-background-jobs
7Pass RateVanilla LLM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Vanilla LLMSetting=Vanilla baseline2026.06 | 7 | — | — | |
| Full Skill TextSetting=Full Skill Text prompting2026.06 | 5 | -0.142 | -1.41 | |
| S2LSetting=Our method2026.06 | 5 | -0.1808 | -1.11 |