Task-Efficient Routing on Security Curated Task Benchmark 1.0 (test)
0.0021Avg. CostForce Weak
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Force WeakStrategy=Force Weak2026.01 | 0.0021 | 67.2 | 83.5 | |
| CASTERStrategy=CASTER2026.01 | 0.0049 | 23.4 | 86.2 | |
| Force StrongStrategy=Force Strong2026.01 | 0.0064 | — | 85.5 |