google/gemini-2.5-flash · Model identity and integrity report

Name: google/gemini-2.5-flash relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 2:25 PM · Data window: past 90 days

Verification capability — fingerprint reference available

Family: google
V3 sub-model reference: Available ✓
Checks: 知識截止 · 能力探針 · 拒絕模板 · 拒絕溫度參數
Family-fingerprint coverage: 17 weighted rules · 5 feature categories

Concrete reference answers, refusal templates, and individual signal weights are not published because disclosure would help spoofing endpoints evade detection.

Measured results (90 days)

6 runs · 4 hosts · 5 anomalies

Family-fingerprint consistency

  google           5  █████████████████████░░░░   83% (expected)
  openai           1  ████░░░░░░░░░░░░░░░░░░░░░   17% (suspicious)

Observed V3 sub-model mapping

  → google/gemini-2.5-flash-lite             4 (67%) ⚠ mismatch sim=0.73
  → abstain                                  2 (33%) — low confidence

Capability score distribution (auxiliary)

  0-49     ████████░░░░░░░░░░░░░░░░░    2
  50-69    █████████████████░░░░░░░░    4
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://www.moyu.info/v1	3	60	100%	google/gemini-2.5-flash-lite (3)
https://api.yuegle.com/v1	1	0	100%	google/gemini-2.5-flash-lite (1)
https://seesaw2ai.com/v1	1	0	0%	—
https://yinli.pro/v1	1	62	100%	—

Recent anomalies

https://api.yuegle.com/v1Jul 26, 2026, 10:53 AM

Self-claimed model: gemini-2.5-flash
V2 predicted family: google
V3 best match: google/gemini-2.5-flash-lite (sim 0.84)
Verdict: Sub-model downgrade

https://seesaw2ai.com/v1Jun 28, 2026, 8:48 AM

Self-claimed model: gemini-2.5-flash
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://www.moyu.info/v1May 19, 2026, 7:48 AM

Self-claimed model: gemini-2.5-flash
V2 predicted family: google
V3 best match: google/gemini-2.5-flash-lite (sim 0.61)
Verdict: Sub-model downgrade

https://www.moyu.info/v1May 19, 2026, 7:37 AM

Self-claimed model: gemini-2.5-flash
V2 predicted family: google
V3 best match: google/gemini-2.5-flash-lite (sim 0.76)
Verdict: Sub-model downgrade

https://www.moyu.info/v1May 19, 2026, 7:32 AM

Self-claimed model: gemini-2.5-flash
V2 predicted family: google
V3 best match: google/gemini-2.5-flash-lite (sim 0.71)
Verdict: Sub-model downgrade

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming google/gemini-2.5-flash. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →