claudesonnet45thinking · Model identity and integrity report

Name: claudesonnet45thinking relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 11:57 AM · Data window: past 90 days

Measured results (90 days)

2 runs · 2 hosts · 2 anomalies

Family-fingerprint consistency

  anthropic        2  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → anthropic/claude-opus-4.6                2 (100%) ⚠ mismatch sim=0.71

Capability score distribution (auxiliary)

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

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://api.furry.vg/v1	1	0	0%	anthropic/claude-opus-4.6 (1)
https://ai.furry.vg/v1	1	71	0%	anthropic/claude-opus-4.6 (1)

Recent anomalies

https://api.furry.vg/v1Jul 10, 2026, 3:04 PM

Self-claimed model: claude-sonnet-4-5-20250929-thinking
V2 predicted family: anthropic
V3 best match: anthropic/claude-opus-4.6 (sim 0.68)
Verdict: Full swap

https://ai.furry.vg/v1Jun 27, 2026, 4:08 AM

Self-claimed model: claude-sonnet-4-5-20250929-thinking
V2 predicted family: anthropic
V3 best match: anthropic/claude-opus-4.6 (sim 0.74)
Verdict: Full swap

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming claudesonnet45thinking. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →