← Back to model

gemini31prolow · Model identity and integrity report

Last updated：Sep 26, 2026, 11:44 AM · Data window: past 90 days

Measured results (90 days)

6 runs · 5 hosts · 6 anomalies

Family-fingerprint consistency

  google           4  █████████████████░░░░░░░░   67% (suspicious)
  anthropic        2  ████████░░░░░░░░░░░░░░░░░   33% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  4 (67%) — low confidence
  → google/gemini-3.1-pro-preview            1 (17%) ⚠ mismatch sim=0.98
  → google/gemini-3.1-flash-lite-preview     1 (17%) ⚠ mismatch sim=0.93

Capability score distribution (auxiliary)

  0-49     █████████████████████░░░░    5
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ████░░░░░░░░░░░░░░░░░░░░░    1
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://www.shenlanqaq.com/v1	2	0	0%	—
https://api.ikuncode.ai/v1	1	0	0%	—
https://aliceclub.top/v1	1	0	0%	—
https://llm-all.pro/v1	1	0	0%	google/gemini-3.1-pro-preview (1)
https://nexaxis.ai/v1	1	76	0%	google/gemini-3.1-flash-lite-preview (1)

Recent anomalies

https://www.shenlanqaq.com/v1Sep 24, 2026, 3:48 PM

Self-claimed model: gemini-3.1-pro-low
V2 predicted family: google
V3 best match: —
Verdict: Full swap

https://www.shenlanqaq.com/v1Sep 24, 2026, 3:36 PM

Self-claimed model: gemini-3.1-pro-low
V2 predicted family: anthropic
V3 best match: —
Verdict: Full swap

https://api.ikuncode.ai/v1Sep 21, 2026, 6:24 PM

Self-claimed model: gemini-3.1-pro-low
V2 predicted family: google
V3 best match: —
Verdict: Full swap

https://aliceclub.top/v1Sep 3, 2026, 4:45 PM

Self-claimed model: [反重力]gemini-3.1-pro-low
V2 predicted family: anthropic
V3 best match: —
Verdict: Family mismatch

https://llm-all.pro/v1Aug 7, 2026, 6:24 PM

Self-claimed model: gemini-3.1-pro-low
V2 predicted family: google
V3 best match: google/gemini-3.1-pro-preview (sim 0.98)
Verdict: Full swap

https://nexaxis.ai/v1Jul 3, 2026, 6:35 PM

Self-claimed model: gemini-3.1-pro-low
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 gemini31prolow. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →