gemini3proimagepreview · Model identity and integrity report

Name: gemini3proimagepreview relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 11:54 AM · Data window: past 90 days

Measured results (90 days)

1 runs · 1 hosts · 1 anomalies

Family-fingerprint consistency

  google           1  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → google/gemini-3.1-pro-preview            1 (100%) ⚠ mismatch sim=0.77

Capability score distribution (auxiliary)

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

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
http://114.132.240.246/v1	1	41	0%	google/gemini-3.1-pro-preview (1)

Recent anomalies

http://114.132.240.246/v1Jun 18, 2026, 6:51 AM

Self-claimed model: gemini-3-pro-image-preview
V2 predicted family: google
V3 best match: google/gemini-3.1-pro-preview (sim 0.77)
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 gemini3proimagepreview. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →