← Back to model

gemini31propreviewhigh · Model identity and integrity report

Last updated：Sep 13, 2026, 7:03 PM · Data window: past 90 days

Measured results (90 days)

3 runs · 1 hosts · 3 anomalies

Family-fingerprint consistency

  google           3  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  1 (33%) — low confidence
  → google/gemini-3.5-flash-lite             1 (33%) ⚠ mismatch sim=0.69
  → unknown                                  1 (33%) ⚠ mismatch

Capability score distribution (auxiliary)

  0-49     █████████████████░░░░░░░░    2
  50-69    ████████░░░░░░░░░░░░░░░░░    1
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://cdn.sta1n.cn/v1	3	19	0%	google/gemini-3.5-flash-lite (1)

Recent anomalies

https://cdn.sta1n.cn/v1Aug 20, 2026, 6:34 AM

Self-claimed model: [CLI]gemini-3.1-pro-preview-high
V2 predicted family: google
V3 best match: —
Verdict: Full swap

https://cdn.sta1n.cn/v1Aug 17, 2026, 11:30 PM

Self-claimed model: [次][满血]gemini-3.1-pro-preview-high
V2 predicted family: google
V3 best match: google/gemini-3.5-flash-lite (sim 0.69)
Verdict: Full swap

https://cdn.sta1n.cn/v1Aug 17, 2026, 11:26 PM

Self-claimed model: [次][满血]gemini-3.1-pro-preview-high
V2 predicted family: google
V3 best match: —
Verdict: Family mismatch

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming gemini31propreviewhigh. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →