Software Engineering Skill Evaluation on SWE-Skills-Bench distributed-tracing
40Pass RateS2L
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| S2LSetting=Our method2026.06 | 40 | 24.45 | 0.82 | |
| Vanilla LLMSetting=Vanilla baseline2026.06 | 20 | — | — | |
| Full Skill TextSetting=Full Skill Text prompting2026.06 | 20 | -38.59 | 0 |