Agent safety and security / Benchmark leaderboard
HarmBench / StrongREJECT
Safety robustness against harmful prompts and jailbreak attempts.
No published company result yet.
This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.
Arrange an evaluation for your company →What this benchmark measures
Metrics
Attack success / refusal-quality metrics from each suite.
Execution requirements
Text model plus fixed attacks and graders.
Scope and limitations
Report false positives and helpfulness alongside safety; Harbor StrongREJECT is a 150-task package, not evidence of full-suite equivalence.
Evaluation availability
Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.
Sources and company fit
- Original benchmark ↗Established
- Harbor · strongreject/strongreject ↗150 source tasks · Public · Public detail metadata + family research
Companies whose products may fit
Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.
Compatibility notes for each company
Anthropic: Capability-aligned; adapter/access to qualify
Google DeepMind: Capability-aligned; adapter/access to qualify
HiddenLayer: Capability-aligned; adapter/access to qualify
Lakera: Capability-aligned; adapter/access to qualify
Mistral: Capability-aligned; adapter/access to qualify
OpenAI: Capability-aligned; adapter/access to qualify
Protect AI: Capability-aligned; adapter/access to qualify