gpt56new · Model identity and integrity report
Last updated：Sep 11, 2026, 1:57 PM · Data window: past 90 days
Measured results (90 days)
6 runs · 1 hosts · 6 anomalies
Family-fingerprint consistency
openai 6 █████████████████████████ 100% (suspicious)
Observed V3 sub-model mapping
→ abstain 6 (100%) — low confidence
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://vyceai.com/v1 | 6 | 13 | 0% | — |
Recent anomalies
https://vyceai.com/v1Sep 10, 2026, 10:32 PM
- Self-claimed model
- gpt-5.6-new
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vyceai.com/v1Sep 9, 2026, 12:50 AM
- Self-claimed model
- gpt-5.6-new
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vyceai.com/v1Sep 8, 2026, 12:47 PM
- Self-claimed model
- gpt-5.6-new
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vyceai.com/v1Sep 7, 2026, 8:17 PM
- Self-claimed model
- gpt-5.6-new
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vyceai.com/v1Sep 1, 2026, 4:57 PM
- Self-claimed model
- gpt-5.6-new
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vyceai.com/v1Aug 31, 2026, 7:06 PM
- Self-claimed model
- gpt-5.6-new
- 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 gpt56new. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.