Software Engineering Skill Evaluation on SWE-Skills-Bench performance-optimization v3
0Pass RateVanilla LLM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Vanilla LLMSetting=Vanilla baseline2026.06 | 0 | — | — | |
| Full Skill TextSetting=Full Skill Text prompting2026.06 | 0 | -33.27 | 0 | |
| S2LSetting=Our method2026.06 | 0 | -45.91 | 0 |