gemini31prohigh · Model identity and integrity report

Name: gemini31prohigh relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 11:56 AM · Data window: past 90 days

Measured results (90 days)

8 runs · 4 hosts · 7 anomalies

Family-fingerprint consistency

  openai           4  █████████████░░░░░░░░░░░░   50% (suspicious)
  google           3  ██████████░░░░░░░░░░░░░░░   38% (suspicious)
  unknown          1  ███░░░░░░░░░░░░░░░░░░░░░░   13% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  4 (50%) — low confidence
  → google/gemini-3.1-flash-lite-preview     2 (25%) ⚠ mismatch sim=0.93
  → openai/gpt-5.4                           1 (13%) ⚠ mismatch sim=1.00
  → unknown                                  1 (13%) ⚠ mismatch

Capability score distribution (auxiliary)

  0-49     ████████████████░░░░░░░░░    5
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ██████████░░░░░░░░░░░░░░░    3
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://mzlone.top/v1	5	16	0%	openai/gpt-5.4 (1)
https://api2.meeyo.org/v1	1	71	0%	—
https://nexaxis.ai/v1	1	76	0%	google/gemini-3.1-flash-lite-preview (1)
https://new.xfxai.top/v1	1	0	0%	google/gemini-3.1-flash-lite-preview (1)

Recent anomalies

https://api2.meeyo.org/v1Jul 14, 2026, 10:13 AM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: google
V3 best match: —
Verdict: V3 low confidence · Abstain

https://mzlone.top/v1Jul 3, 2026, 6:48 PM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: openai
V3 best match: openai/gpt-5.4 (sim 1.00)
Verdict: Full swap

https://nexaxis.ai/v1Jul 3, 2026, 6:32 PM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: google
V3 best match: google/gemini-3.1-flash-lite-preview (sim 0.93)
Verdict: Full swap

https://mzlone.top/v1Jun 26, 2026, 2:31 PM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://mzlone.top/v1Jun 26, 2026, 2:29 PM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://mzlone.top/v1Jun 25, 2026, 7:38 PM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://new.xfxai.top/v1Jun 24, 2026, 11:32 PM

Self-claimed model: [ant]gemini-3.1-pro-high
V2 predicted family: google
V3 best match: google/gemini-3.1-flash-lite-preview (sim 0.93)
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 gemini31prohigh. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →