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

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