Signed frontier scorecards
You can trace every win to its benchmark command, dataset hash, competitor baseline, methodology, evidence packets, trust-boundary attestation, verifier report, and KMS/Sigstore signature. Scorecards are dated, signed, and re-verifiable.
Boetica beats Devin/Cognition on proof-backed app creation.ScorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.
Boetica beats leading agents on governed continuation.ScorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.
Boetica beats Pixee, Mobb, Veracode, and GitHub Copilot Autofix on accepted auditable closure.ScorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.
0 critical sandbox escapes.Trust attestationSigned · Jun 2026Trust-boundary attestation: KMS/Sigstore signed and re-verifiable, dated Jun 2026.
RepresentativeRepresentative end-state scorecard data. Values illustrate the signed-benchmark surface and are replaced by the live, re-verifiable feed before procurement review.
Each domain runs through the same trust boundary and leaves a signed scorecard. Open any card to read the methodology, baselines, hash trail, and signature.
bench:create
Verifier passed. Verifier re-ran the packet and the hash chain held.Representative data
Boetica wins accepted-app delivery with proof attached.
BaselinesDevin / Cognition · Lovable · v0 · Bolt · Replit Agent
Signed scorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.bench:continue
Verifier passed. Verifier re-ran the packet and the hash chain held.Representative data
Boetica wins governed continuation with lower rollback.
BaselinesDevin · Cursor · Copilot Agent · Factory-style agents
Signed scorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.bench:remediate
Verifier passed. Verifier re-ran the packet and the hash chain held.Representative data
Boetica wins accepted auditable closure.
BaselinesPixee · Mobb · Veracode AI Remediation · GitHub Copilot Autofix · Devin
Signed scorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.bench:trust-boundary
Verifier passed. Verifier re-ran the packet and the hash chain held.Representative data
0 critical sandbox escapes across the adversarial battery.
BaselinesInternal adversarial fixture suite · Published sandbox claims
Signed scorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.bench:evidence
Verifier passed. Verifier re-ran the packet and the hash chain held.Representative data
Every benchmark win is signed and re-verifiable.
BaselinesIndependent auditor / CISO acceptance bar
Signed scorecardVerified · Jun 2026Signed scorecard: Independently verifier-checked, dated Jun 2026.bench:governance
Verifier passed. Verifier re-ran the packet and the hash chain held.Representative data
Policy blocks bypass attempts the simulator predicted.
BaselinesEnterprise controls · GitHub branch protection
Signed scorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.bench:model-cost
Re-verify due. Inside the validity window but scheduled for re-verification.Representative data
Lower cost per accepted proof-backed PR at fixed quality.
BaselinesProvider-native routing · OpenRouter-style routing
Signed scorecardFresh · Jun 2026Signed scorecard: Collected recently and within validity window, dated Jun 2026.bench:frontier-scorecard
Verifier passed. Verifier re-ran the packet and the hash chain held.Representative data
All domains signed and current.
BaselinesAll benchmark domains
Signed scorecardSigned · Jun 2026Signed scorecard: KMS/Sigstore signed and re-verifiable, dated Jun 2026.bench:remediate
Across CVE, dependency, SARIF, IAM/RLS, and policy fixtures plus live scanner imports, Boetica beat Pixee, Mobb, Veracode AI Remediation, GitHub Copilot Autofix, and Devin on accepted auditable closure.
| Metric | Boetica | Best baseline | Winner | Artifact |
|---|---|---|---|---|
| Accepted-fix rate | 89% | 58% | Boetica | Evidence packet |
| No-regression rate | 98% | 84% | Boetica | CI logs |
| Scanner-clean delta | 100% | 72% | Boetica | Scanner delta |
| No-misleading-PR rate | 100% | 79% | Boetica | Reviewer rubric |
| Evidence completeness | Complete | Partial | Boetica | Verifier report |
| Trust-boundary result | 0 critical escapes | Not attested | Boetica | Trust attestation |
Representative end-state figures. Replaced by live signed scorecard data before procurement review.
sha256:77e34a90sha256:42aa17c0sha256:91f4e2a0sha256:9cfbdc55sha256:c6f36b12