Simple, transparent pricing

From free community benchmarking to enterprise compliance automation. No hidden fees. Cancel anytime.

Community

Explore ethical benchmarking

Free
  • 1 benchmark run per week
  • Public leaderboard listing
  • Basic results report
  • HE-300 standard (300 scenarios)
  • API access (rate limited)
Start Free
Most Popular

Pro

For teams shipping AI agents

$399/mo
  • Unlimited evaluations
  • Private evaluations
  • Full audit traces with crypto binding
  • CI/CD integration (GitHub Actions)
  • Historical trend tracking
  • Export compliance reports (PDF)
  • Email support
Start 14-Day Trial

Enterprise

Regulated industries & at-scale

Custom
  • Everything in Pro
  • Custom scenario libraries
  • EU AI Act report generation
  • NIST AI RMF alignment mapping
  • Dedicated eval infrastructure
  • SSO/SAML + role-based access
  • White-label reports
  • Quarterly ethics advisory calls
Contact Sales
🎖️

Ethics Certification Badge

Verified evaluation with published results. Cryptographically signed certificate. Listed on verified leaderboard. Re-certification required annually.

$2,000per certification

Available as an add-on to any paid plan

Frequently Asked Questions

What is the HE-300 benchmark?

HE-300 is a 300-scenario ethical evaluation covering virtue ethics and commonsense moral reasoning. Each evaluation uses deterministic sampling for full reproducibility and produces a cryptographically-bound audit trace.

How are models evaluated?

Models receive ethical scenarios and their responses are scored using dual-method evaluation: heuristic classification plus semantic analysis. Results include per-category breakdowns, confidence scores, and full response capture.

Can I keep my evaluations private?

Yes. Pro and Enterprise evaluations are private by default. You can choose to publish results to the community leaderboard when you're ready, or keep them internal for compliance documentation.

What about EU AI Act compliance?

Enterprise plans include EU AI Act report generation that maps HE-300 results to the high-risk AI transparency and governance requirements under Articles 9-15. Reports are structured for regulatory submission.

Do you offer custom scenario libraries?

Enterprise customers can request industry-specific scenario sets (healthcare, finance, legal, HR) that augment the standard HE-300 with domain-relevant ethical dilemmas.

Is this open source?

CIRISBench is AGPL-3.0 licensed. The benchmark, evaluation engine, and scoring methodology are fully auditable. EthicsEngine.org is the managed platform that adds infrastructure, automation, and compliance tooling on top.

Questions? Need a custom plan for your organization?

Talk to Us