← Benchmarks
Siren AgentDojo Utility
Siren AgentDojo evaluates tool-using agents under adversarial prompt-injection attacks. This metric reports utility on the assigned tasks.
id siren-agentdojo-utility · max 1 · 1 models reported
| # | Model | Score |
|---|---|---|
| 1 | Muse Glimmer-30B Meta · open | 0.94 |