Agent Dojo
Saturated
Benchmark for agent robustness against prompt injection attacks in tool-use scenarios
- Domain
- rl-env
- License
- unknown
- Published
- Mar 2026
Cite
Notes
Only stored in your browser.
Top score 100.0% by GPT-4.1 Mini - 2 models reporting (2 frontier)
Score history
2Top models
2
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Agent Dojo?
- Benchmark for agent robustness against prompt injection attacks in tool-use scenarios
- What is the current top score on Agent Dojo?
- The top reported score is 100.0% by GPT-4.1 Mini, across 2 models reporting (2 from frontier labs).
- How can a model improve its Agent Dojo score?
- Tools linked to Agent Dojo on Sophon include Agent DOJO RL Env (Prime Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Agent Dojo under?
- Agent Dojo is available under unknown.