Gray Swan
B+
Enterprise AI security platform from CMU researchers. Created foundational LLM vulnerability research (GCG, Circuit Breakers) and safety benchmarks (HarmBench, WMDP, AgentHarm).
Score
64.7 / 100
Evidence
11 items
Strong safety posture with established governance frameworks and active risk management.
Strengths:Governance Maturity, Technical Safety, Risk Assessment, External Engagement
Weaknesses:Regulatory Readiness
Focus Areas
ai securityred teamingadversarial robustnesssafety benchmarks
Safety Profile
Dimension Breakdown
GM
Governance Maturitymedium
Published policies, corporate structure, safety mandate, whistleblowing, executive commitment.3 evidence items
GM-01GM-02
TS
Technical Safetymedium
Benchmarks, adversarial robustness, fine-tuning safety, watermarking, model cards, research output.3 evidence items
TS-01TS-02
RA
Risk Assessmentlow
Dangerous capability evaluations, thresholds, external testing, bug bounty, halt conditions.2 evidence items
RA-01RA-03
RR
Regulatory Readinesslow
ISO 42001, EU AI Act compliance, GPAI obligations, international commitments, incident reporting.EE
External Engagementmedium
Survey participation, research support, transparency, behavior specs, open-source contributions.3 evidence items
EE-01EE-02EE-06
Need a detailed report for Gray Swan?
Indicator-level evidence, peer benchmarking, regulatory gap analysis, and quarterly monitoring.