← Back to model

gemini31prohigh · Model identity and integrity report

Last updated：Sep 13, 2026, 9:57 PM · Data window: past 90 days

Measured results (90 days)

18 runs · 12 hosts · 17 anomalies

Family-fingerprint consistency

  google          10  ██████████████░░░░░░░░░░░   56% (suspicious)
  openai           4  ██████░░░░░░░░░░░░░░░░░░░   22% (suspicious)
  anthropic        3  ████░░░░░░░░░░░░░░░░░░░░░   17% (suspicious)
  unknown          1  ██░░░░░░░░░░░░░░░░░░░░░░░    6% (suspicious)

Observed V3 sub-model mapping

  → abstain                                 11 (61%) — low confidence
  → google/gemini-3.1-flash-lite-preview     3 (17%) ⚠ mismatch sim=0.84
  → google/gemini-3.5-flash-lite             1 ( 6%) ⚠ mismatch sim=0.71
  → google/gemini-3.1-pro-preview            1 ( 6%) ⚠ mismatch sim=0.79
  → openai/gpt-5.4                           1 ( 6%) ⚠ mismatch sim=1.00
  → unknown                                  1 ( 6%) ⚠ mismatch

Capability score distribution (auxiliary)

  0-49     ██████████████░░░░░░░░░░░   10
  50-69    ███░░░░░░░░░░░░░░░░░░░░░░    2
  70-89    ████████░░░░░░░░░░░░░░░░░    6
  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://hahacode.com/v1	2	81	0%	google/gemini-3.5-flash-lite (1)
https://nexaxis.ai/v1	2	38	0%	google/gemini-3.1-flash-lite-preview (1)
https://aliceclub.top/v1	1	0	0%	—
https://cwld.cc.cd/v1	1	0	0%	—
https://image.123uq.com/v1	1	81	0%	—
https://www.poke2api.com/v1	1	60	0%	google/gemini-3.1-flash-lite-preview (1)
https://www.ggwk1.online/v1	1	58	0%	—
https://api.relaycore.cn/v1	1	0	0%	—
https://api.1314mc.net/v1	1	0	0%	google/gemini-3.1-pro-preview (1)
https://api2.meeyo.org/v1	1	71	0%	—
https://new.xfxai.top/v1	1	0	0%	google/gemini-3.1-flash-lite-preview (1)

Recent anomalies

https://hahacode.com/v1Sep 4, 2026, 6:27 AM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: google
V3 best match: google/gemini-3.5-flash-lite (sim 0.71)
Verdict: Full swap

https://aliceclub.top/v1Sep 3, 2026, 4:49 PM

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

https://cwld.cc.cd/v1Sep 3, 2026, 4:40 AM

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

https://image.123uq.com/v1Sep 3, 2026, 2:46 AM

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

https://www.poke2api.com/v1Aug 10, 2026, 6:00 PM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: anthropic
V3 best match: google/gemini-3.1-flash-lite-preview (sim 0.67)
Verdict: Full swap

https://hahacode.com/v1Aug 9, 2026, 2:33 AM

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

https://www.ggwk1.online/v1Aug 7, 2026, 5:57 PM

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

https://api.relaycore.cn/v1Aug 2, 2026, 11:44 PM

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

https://api.1314mc.net/v1Aug 2, 2026, 5:25 PM

Self-claimed model: gemini-3.1-pro-high
V2 predicted family: google
V3 best match: google/gemini-3.1-pro-preview (sim 0.78)
Verdict: Full swap

https://nexaxis.ai/v1Aug 2, 2026, 1:11 PM

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

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 →