← Back to model

gemini38flashhigh · Model identity and integrity report

Last updated：Sep 5, 2026, 7:30 AM · Data window: past 90 days

Measured results (90 days)

7 runs · 3 hosts · 7 anomalies

Family-fingerprint consistency

  google           6  ██████████████████████░░░   86% (suspicious)
  anthropic        1  ████░░░░░░░░░░░░░░░░░░░░░   14% (suspicious)

Observed V3 sub-model mapping

  → google/gemini-3.6-flash                  6 (86%) ⚠ mismatch sim=0.72
  → abstain                                  1 (14%) — low confidence

Capability score distribution (auxiliary)

  0-49     ███████████░░░░░░░░░░░░░░    3
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ██████████████░░░░░░░░░░░    4
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://yjapi.manqiaotechnology.com/v1	4	19	0%	google/gemini-3.6-flash (3)
https://api.chhlink.xyz/v1	2	73	0%	google/gemini-3.6-flash (2)
https://sub.xiiqtg.vip/v1	1	80	0%	google/gemini-3.6-flash (1)

Recent anomalies

https://sub.xiiqtg.vip/v1Sep 4, 2026, 5:06 PM

Self-claimed model: gemini-3.8-flash-high
V2 predicted family: google
V3 best match: google/gemini-3.6-flash (sim 0.73)
Verdict: Full swap

https://yjapi.manqiaotechnology.com/v1Sep 4, 2026, 11:58 AM

Self-claimed model: gemini-3.8-flash-high
V2 predicted family: google
V3 best match: google/gemini-3.6-flash (sim 0.73)
Verdict: Full swap

https://yjapi.manqiaotechnology.com/v1Sep 4, 2026, 11:43 AM

Self-claimed model: gemini-3.8-flash-high
V2 predicted family: anthropic
V3 best match: —
Verdict: V3 low confidence · Abstain

https://yjapi.manqiaotechnology.com/v1Sep 4, 2026, 10:22 AM

Self-claimed model: gemini-3.8-flash-high
V2 predicted family: google
V3 best match: google/gemini-3.6-flash (sim 0.73)
Verdict: Full swap

https://yjapi.manqiaotechnology.com/v1Sep 4, 2026, 2:55 AM

Self-claimed model: gemini-3.8-flash-high
V2 predicted family: google
V3 best match: google/gemini-3.6-flash (sim 0.73)
Verdict: Full swap

https://api.chhlink.xyz/v1Sep 3, 2026, 7:52 AM

Self-claimed model: gemini-3.8-flash-high
V2 predicted family: google
V3 best match: google/gemini-3.6-flash (sim 0.73)
Verdict: Full swap

https://api.chhlink.xyz/v1Sep 3, 2026, 7:33 AM

Self-claimed model: gemini-3.8-flash-high
V2 predicted family: google
V3 best match: google/gemini-3.6-flash (sim 0.73)
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 gemini38flashhigh. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →