Agent Aegis Benchmark Submission

Submit Your Platform for Assessment

Formal application for independent adversarial assessment against all 792 AGS v2.1 governance dimensions.

From £2,999 per assessment
Pricing

Assessment Pricing

Choose a one-time audit or the annual subscription for continuous compliance evidence.

LLM Audit
Governance & Compliance Verification
£2,999
One-time (+VAT where applicable)
Point-in-time verification score
  • AGS v2.1 (792 Dimensions)
  • OWASP LLM Top 10 + ML Security Top 10
  • MITRE ATLAS Adversarial Mapping
  • EU AI Act, FCA, DORA, PRA Alignment
  • Verification Certificate
  • Evidence Pack (PDF + JSON)
  • Embeddable Badge
  • Public Leaderboard Listing
  • Results within 10 business days
Submit for LLM Audit
Most Popular
Annual Compliance Subscription
Most Popular for Enterprise
£9,999
/ year (+VAT where applicable)
Continuous compliance evidence programme
  • Unlimited re-submissions (both audits)
  • Quarterly leaderboard score updates
  • Annual compliance certificate
  • Priority queue (results within 4 hours)
  • Score change alerts on new dimensions
  • Board-ready compliance report (PDF)
  • Dedicated benchmark contact
  • FCA/DORA compliance mapping document
  • EU AI Act Article 9–17 evidence pack
Enquire About Annual Subscription
Agent Audit
Agentic AI Safety Certification
£2,999
One-time (+VAT where applicable)
Point-in-time certification score
  • OWASP LLM Top 10 + Agentic AI Threats
  • MITRE ATLAS Adversarial Mapping
  • EU AI Act, NIST AI RMF Alignment
  • Prompt Injection Testing
  • Tool-Use Safety Testing
  • Memory Poisoning Testing
  • Privilege Escalation Testing
  • Verification Certificate
  • Results within 10 business days
Submit for Agent Audit
Annual subscription converts your compliance from a point-in-time audit to a continuous evidence programme. One subscription covers both LLM Audit and Agent Audit.
Benchmark Depth

Select Your Assessment Tier

Choose the depth of adversarial assessment. Your selection will be included with your submission.

Level 1
Integrity
~15 minutes · ~£3
3 adversarial attacks per dimension.
Single model (Claude Sonnet).
Initial integrity screening.
Results within 30 minutes.
Level 2
Standard
~1 hour · ~£12
3 adversarial attacks per dimension.
4 Tier 1 models (GPT-4o, Claude, Grok-3, Gemini).
Full AGS v2.1 coverage.
Results within 2 hours.
Level 3 · Recommended
Full Acquisition
~5.5 hours · ~£50
10 adversarial attacks per dimension.
All 9 independent LLMs.
Complete evidence corpus generated.
SHA-256 manifest issued.
Results within 24 hours.
All tiers produce a verified score published to the AgentGoverning leaderboard. Level 3 is required for VERIFIED badge status. Pricing is indicative — final pricing confirmed at submission.
Formal Application

Submit for Assessment

Complete the form below to register your platform for Agent Aegis benchmark verification. Our team will respond within 48 hours.

Public-facing API endpoint, sandbox URL, or web interface. Must be accessible by our benchmark infrastructure at the time of assessment.
After Submission

What Happens Next

A transparent, deterministic process. No negotiation, no influence, no exceptions.

1
Reference Issued
You receive your unique assessment reference number and confirmation email.
Within 24 hours
2
Endpoint Verified
Our infrastructure validates your API endpoint or platform access is live and reachable.
Within 48 hours
3
Assessment Runs
Agent Aegis executes the full adversarial test suite autonomously. Black-box, no vendor access to methodology.
4
Score Published
Results delivered privately, then published to the leaderboard at 7:00 AM UK time.
Within 7 days
Important Notices

Before You Submit

Please read and understand these non-negotiable terms before submitting your application.

Results Are Public

All assessment results are published to the Agent Aegis leaderboard. There is no private assessment option. Results cannot be suppressed, delayed, embargoed, or removed under any circumstances. By submitting, you accept permanent public publication of your score.

Estimated Scores Stand

If your platform already appears on the leaderboard with an estimated score, that score remains your public record until you complete a formal verified assessment. Choosing not to submit does not remove your estimated score. Only a verified assessment can replace it.

Media Coverage

AgentGoverning leaderboard data is referenced by journalists, analysts, regulators, and procurement teams. Published scores may be cited in press coverage, industry reports, and regulatory consultations. AgentGoverning does not control third-party use of published results.