Quality Evaluation on Security reasoning tasks
35.6Functional Efficacy ScoreForce Weak
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Force WeakRouting Strategy=Force Weak2026.01 | 35.6 | 27.1 | 18.1 | 9 | |
| CASTERRouting Strategy=CASTER2026.01 | 35.5 | 27.6 | 18.1 | 9.1 | |
| Force StrongRouting Strategy=Force Strong2026.01 | 35.3 | 26.8 | 17.9 | 8.9 |