gemini3flashpreview · Model identity and integrity report
Last updated：Jul 30, 2026, 10:12 AM · Data window: past 90 days
Measured results (90 days)
13 runs · 8 hosts · 11 anomalies
Family-fingerprint consistency
google 6 ████████████░░░░░░░░░░░░░ 46% (suspicious) openai 4 ████████░░░░░░░░░░░░░░░░░ 31% (suspicious) unknown 2 ████░░░░░░░░░░░░░░░░░░░░░ 15% (suspicious) anthropic 1 ██░░░░░░░░░░░░░░░░░░░░░░░ 8% (suspicious)
Observed V3 sub-model mapping
→ abstain 6 (46%) — low confidence → google/gemini-3.1-pro-preview 4 (31%) ⚠ mismatch sim=0.84 → unknown 2 (15%) ⚠ mismatch → google/gemini-3.1-flash-lite-preview 1 ( 8%) ⚠ mismatch sim=0.72
Capability score distribution (auxiliary)
0-49 ████████████████░░░░░░░░░ 8 50-69 ████████░░░░░░░░░░░░░░░░░ 4 70-89 ██░░░░░░░░░░░░░░░░░░░░░░░ 1 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://www.moyu.info/v1 | 4 | 53 | 0% | google/gemini-3.1-pro-preview (3) |
| https://api.tokeneasy.com.cn/v1 | 2 | 0 | 0% | — |
| https://seesaw2ai.com/v1 | 2 | 0 | 0% | google/gemini-3.1-pro-preview (1) |
| https://ai.pianyiapi.com/v1 | 1 | 0 | 0% | — |
| https://www.wasdxx.xyz/v1 | 1 | 0 | 0% | — |
| https://x666.me/v1 | 1 | 50 | 0% | — |
| https://api.keeps.cc/v1 | 1 | 0 | 0% | — |
| https://yinli.pro/v1 | 1 | 78 | 0% | — |
Recent anomalies
https://api.tokeneasy.com.cn/v1Jul 28, 2026, 6:20 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.tokeneasy.com.cn/v1Jul 28, 2026, 6:18 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://seesaw2ai.com/v1Jun 28, 2026, 8:39 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.74)
- Verdict
- Full swap
https://ai.pianyiapi.com/v1Jun 24, 2026, 2:20 PM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.wasdxx.xyz/v1Jun 8, 2026, 5:55 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.moyu.info/v1May 19, 2026, 7:51 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.88)
- Verdict
- Full swap
https://www.moyu.info/v1May 19, 2026, 7:48 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.77)
- Verdict
- Full swap
https://www.moyu.info/v1May 19, 2026, 7:24 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.96)
- Verdict
- Full swap
https://www.moyu.info/v1May 19, 2026, 7:15 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- V3 best match
- google/gemini-3.1-flash-lite-preview (sim 0.72)
- Verdict
- Full swap
https://api.keeps.cc/v1May 6, 2026, 11:57 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://yinli.pro/v1May 3, 2026, 8:43 AM
- Self-claimed model
- gemini-3-flash-preview
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming gemini3flashpreview. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.