gpt56 · Model identity and integrity report
Last updated：Sep 13, 2026, 9:23 PM · Data window: past 90 days
Measured results (90 days)
72 runs · 62 hosts · 60 anomalies
Family-fingerprint consistency
openai 55 ███████████████████░░░░░░ 76% (suspicious) unknown 12 ████░░░░░░░░░░░░░░░░░░░░░ 17% (suspicious) anthropic 3 █░░░░░░░░░░░░░░░░░░░░░░░░ 4% (suspicious) deepseek 2 █░░░░░░░░░░░░░░░░░░░░░░░░ 3% (suspicious)
Observed V3 sub-model mapping
→ abstain 54 (75%) — low confidence → unknown 16 (22%) ⚠ mismatch → deepseek/deepseek-v4-flash 1 ( 1%) ⚠ mismatch sim=0.73 → deepseek/deepseek-v4-pro 1 ( 1%) ⚠ mismatch sim=0.72
Capability score distribution (auxiliary)
0-49 ██████████████████░░░░░░░ 51 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 ███████░░░░░░░░░░░░░░░░░░ 21 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://bandelbanget.xyz/v1 | 4 | 0 | 0% | — |
| https://api.x5m5x.com/v1 | 3 | 23 | 0% | — |
| https://gateai.cc/v1 | 2 | 0 | 0% | — |
| https://router.srbyte.dev/v1 | 2 | 0 | 0% | — |
| https://modelgate.app/v1 | 2 | 38 | 0% | deepseek/deepseek-v4-flash (1) |
| https://ai.nexfaro.com/v1 | 2 | 81 | 0% | — |
| https://api.yundzc.cn/v1 | 2 | 0 | 0% | — |
| https://ai.tuava.cn/v1 | 1 | 0 | 0% | — |
| https://www.mcgrox.top/v1 | 1 | 0 | 0% | — |
| https://ohhmyagent.com/v1 | 1 | 76 | 0% | — |
| https://catbee.online/v1 | 1 | 0 | 0% | — |
| https://www.lsgyl.xyz/v1 | 1 | 0 | 0% | — |
| https://nailongapi.top/v1 | 1 | 75 | 0% | — |
| https://token.optoken.cc/v1 | 1 | 76 | 0% | — |
| https://weilaiapi.xyz/v1 | 1 | 0 | 0% | — |
| https://api.kakouai.com/v1 | 1 | 80 | 0% | — |
| https://b05d64095af6.nofx.one/v1 | 1 | 0 | 0% | — |
| https://us-api.x5m5x.com/v1 | 1 | 0 | 0% | — |
| https://wawazz.xyz/v1 | 1 | 0 | 0% | — |
| https://api.wenwenai.org/v1 | 1 | 74 | 0% | — |
| https://www.tokenbook.cc/v1 | 1 | 72 | 0% | — |
| https://codexcn.ccwu.cc/v1 | 1 | 0 | 0% | — |
| https://api.yescode.cloud/v1 | 1 | 0 | 0% | — |
| https://hubway.cc/v1 | 1 | 0 | 0% | — |
| https://api.zeekai.cc/v1 | 1 | 0 | 0% | — |
Recent anomalies
https://ai.tuava.cn/v1Sep 11, 2026, 6:43 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.mcgrox.top/v1Sep 11, 2026, 2:55 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://bandelbanget.xyz/v1Sep 9, 2026, 12:13 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://bandelbanget.xyz/v1Sep 9, 2026, 2:48 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ohhmyagent.com/v1Sep 6, 2026, 4:07 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://catbee.online/v1Sep 4, 2026, 5:16 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://nailongapi.top/v1Sep 4, 2026, 1:23 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://token.optoken.cc/v1Sep 4, 2026, 9:16 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://weilaiapi.xyz/v1Sep 3, 2026, 2:34 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.kakouai.com/v1Sep 2, 2026, 3:47 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://b05d64095af6.nofx.one/v1Sep 2, 2026, 1:49 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://us-api.x5m5x.com/v1Sep 2, 2026, 10:29 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://wawazz.xyz/v1Sep 1, 2026, 3:03 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.wenwenai.org/v1Sep 1, 2026, 12:34 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.tokenbook.cc/v1Aug 31, 2026, 6:47 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://codexcn.ccwu.cc/v1Aug 31, 2026, 4:27 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.yescode.cloud/v1Aug 30, 2026, 6:56 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.zeekai.cc/v1Aug 29, 2026, 12:33 PM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- Family mismatch
https://gateai.cc/v1Aug 26, 2026, 7:37 AM
- Self-claimed model
- gpt-5.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.aiyoyoo.com/v1Aug 24, 2026, 7:32 AM
- Self-claimed model
- gpt-5.6
- 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 gpt56. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.