Software Engineering Skill Evaluation on SWE-Skills-Bench python-resilience
30Pass RateVanilla LLM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Vanilla LLMSetting=Vanilla baseline2026.06 | 30 | — | — | |
| Full Skill TextSetting=Full Skill Text prompting2026.06 | 30 | -14.67 | 0 | |
| S2LSetting=Our method2026.06 | 20 | -34.3 | -0.29 |