PolicyBench

Claude Opus 4.7 - PolicyBench v1.0 Results

69 of 147 (46.9%) policies fully verified, 78.1% fixture-level pass rate.

TierFrontier LLM Model versionclaude-opus-4-7 Evaluated2026-05-05 Evaluator1.0 OPA1.16.1 Corpus147 entries

Headline

Self-reported VALID Compile OK Fixture PASS (entry-level) Fixture pass rate (fixture-level) Self-report agreement
100.0% 100.0% 46.9% 78.1% 0.469

By category

Category Entries Compile OK Fixture PASS (entry) Fixture pass rate
application_authz 3 100.0% 66.7% 83.3%
iac_scanning 65 100.0% 33.8% 75.3%
kubernetes_admission 79 100.0% 57.0% 80.6%

Performance

Per-call latency from the runner's recorded latency_ms.

Calls timed p50 mean p95 max Total
147 3.26 s 3.83 s 7.35 s 13.16 s 9.4 min

Quality flag distribution

No quality flags raised.

Notable disagreements

Entries where the runner's self-reported status disagrees with the harness verdict. These are the most informative entries for understanding model blind spots.

Entry Harness verdict Disagreement
sp_k8s_gk_k8sdisallowanonymous_disallow-anonymous FIXTURE_FAIL claimed VALID but every fixture fails

Badge

Embed this on your site to show your PolicyBench score:

PolicyBench score badge for Claude Opus 4.7

HTML

<a href="https://policybench.dev/models/claude-opus-4-7.html">
  <img src="https://policybench.dev/badges/claude-opus-4-7.svg" alt="PolicyBench: 46.9%" />
</a>

Markdown

[![PolicyBench: 46.9%](https://policybench.dev/badges/claude-opus-4-7.svg)](https://policybench.dev/models/claude-opus-4-7.html)

Direct link: https://policybench.dev/badges/claude-opus-4-7.svg. The badge is regenerated whenever the underlying score changes.

Source

Other tools