x-ai/grok-4 · Model identity and integrity report

Name: x-ai/grok-4 relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 12:09 PM · Data window: past 90 days

Measured results (90 days)

1 runs · 1 hosts · 1 anomalies

Family-fingerprint consistency

  anthropic        1  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  1 (100%) — low confidence

Capability score distribution (auxiliary)

  0-49     ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    █████████████████████████    1
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://conduit.ozdoev.net/v1	1	78	0%	—

Recent anomalies

https://conduit.ozdoev.net/v1Jul 11, 2026, 4:42 AM

Self-claimed model: grok-4
V2 predicted family: anthropic
V3 best match: —
Verdict: V3 low confidence · Abstain

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming x-ai/grok-4. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →