Siren AgentDojo Attack Success Rate
Progress Over Time
Interactive timeline showing model performance evolution on Siren AgentDojo Attack Success Rate
Siren AgentDojo Attack Success Rate Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Meta | 30B | — | — |
What is Siren AgentDojo Attack Success Rate?
Siren AgentDojo evaluates tool-using agents under adversarial prompt-injection attacks. This metric is the attack success rate; lower is better.
Siren AgentDojo Attack Success Rate is a text benchmark evaluating models on safety, agents, and tool calling tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.3, with the leader at 0.3.
Compare leaders on the best AI for safety, best AI for agents and best AI for tool calling leaderboards.
Current leaders
Muse Glimmer-30B from Meta currently leads the Siren AgentDojo Attack Success Rate leaderboard with a score of 0.284 across 1 evaluated AI models.
FAQ
Common questions about the Siren AgentDojo Attack Success Rate benchmark and leaderboard.