gpt55 · Model identity and integrity report
Last updated：Sep 13, 2026, 9:23 PM · Data window: past 90 days
Measured results (90 days)
3125 runs · 1253 hosts · 2919 anomalies
Family-fingerprint consistency
openai 2812 ███████████████████████░░ 90% (suspicious) unknown 206 ██░░░░░░░░░░░░░░░░░░░░░░░ 7% (suspicious) anthropic 96 █░░░░░░░░░░░░░░░░░░░░░░░░ 3% (suspicious) google 4 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) deepseek 2 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) qwen 2 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) zhipu 2 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) meta 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious)
Observed V3 sub-model mapping
→ abstain 2513 (80%) — low confidence → unknown 291 ( 9%) ⚠ mismatch → openai/gpt-5.5 192 ( 6%) ⚠ mismatch sim=0.95 → openai/gpt-5.4 101 ( 3%) ⚠ mismatch sim=0.94 → openai/gpt-5.2 9 ( 0%) ⚠ mismatch sim=0.91 → openai/gpt-5.4-mini 7 ( 0%) ⚠ mismatch sim=0.92 → openai/gpt-5-mini 6 ( 0%) ⚠ mismatch sim=0.78 → anthropic/claude-fable-5 2 ( 0%) ⚠ mismatch sim=0.78 → openai/gpt-4.1 1 ( 0%) ⚠ mismatch sim=0.69 → qwen/qwen3-max 1 ( 0%) ⚠ mismatch sim=0.72 → openai/gpt-5 1 ( 0%) ⚠ mismatch sim=0.83 → google/gemini-3.1-pro-preview 1 ( 0%) ⚠ mismatch sim=0.76
Capability score distribution (auxiliary)
0-49 ███████████░░░░░░░░░░░░░░ 1414 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 56 70-89 ██████████░░░░░░░░░░░░░░░ 1184 90-100 ████░░░░░░░░░░░░░░░░░░░░░ 471
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| http://187.53.135.158:7101/v1 | 104 | 0 | 0% | openai/gpt-5-mini (1) |
| https://lingsuan.top/v1 | 32 | 66 | 0% | openai/gpt-5.5 (2) |
| https://mdkj.lol/v1 | 31 | 57 | 0% | openai/gpt-5.5 (2) |
| https://jojocode.com/v1 | 24 | 36 | 0% | openai/gpt-5.4 (5) |
| https://ai.input.im/v1 | 24 | 52 | 0% | openai/gpt-5.5 (2) |
| https://a6api.com/v1 | 22 | 72 | 0% | openai/gpt-5.4 (1) |
| https://ai.furry.vg/v1 | 20 | 49 | 0% | openai/gpt-5.5 (1) |
| https://bobdong.cn/v1 | 20 | 87 | 0% | openai/gpt-5.5 (1) |
| https://www.packyapi.com/v1 | 19 | 31 | 0% | — |
| https://sub2.congmingai.com/v1 | 19 | 56 | 0% | openai/gpt-5.5 (4) |
| https://vip.lcodex.cn/v1 | 19 | 14 | 0% | openai/gpt-5.4 (3) |
| https://new.sharedchat.cc/codex | 17 | 3 | 0% | — |
| https://yunwu.ai/v1 | 17 | 52 | 0% | openai/gpt-5.4 (2) |
| https://aihub.top/v1 | 16 | 33 | 0% | — |
| https://api.mouubox.com/v1 | 16 | 59 | 0% | openai/gpt-5.4 (3) |
| https://www.cctq.ai/v1 | 15 | 68 | 0% | — |
| https://sub.kedaya.xyz/v1 | 15 | 56 | 0% | openai/gpt-5.4 (1) |
| https://api.aijws.com/v1 | 15 | 56 | 0% | — |
| https://sub2api.lyclyc.xyz/v1 | 15 | 75 | 0% | — |
| https://bizdecipher.com/v1 | 14 | 45 | 0% | — |
| https://sarang.id/v1 | 14 | 51 | 0% | — |
| https://api.tokenskingdom.com/v1 | 14 | 79 | 0% | openai/gpt-5.5 (4) |
| https://sub2api.luchikey.com/v1 | 14 | 88 | 0% | openai/gpt-5.5 (1) |
| https://docode.cc/v1 | 13 | 71 | 0% | — |
| https://zz1cc.cc.cd/v1 | 13 | 67 | 0% | openai/gpt-5.5 (1) |
Recent anomalies
https://sub.wanzhao.top/v1Sep 13, 2026, 10:40 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://756777.xyz/v1Sep 13, 2026, 10:23 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ergouapi.com/v1Sep 13, 2026, 9:47 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gatecheap.vn/v1Sep 13, 2026, 6:54 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
http://121.41.29.72:18090/v1Sep 13, 2026, 5:50 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gatecheap.vn/v1Sep 13, 2026, 5:47 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gatecheap.vn/v1Sep 13, 2026, 5:44 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gatecheap.vn/v1Sep 13, 2026, 5:44 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.iiuxx.cfd/v1Sep 13, 2026, 4:50 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- Family mismatch
https://api.easycode.cc.cd/v1Sep 13, 2026, 4:43 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- Family mismatch
https://dmit.m1eepo.de/v1Sep 12, 2026, 8:24 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.fucheers.top/v1Sep 12, 2026, 6:55 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.haokun.de/v1Sep 12, 2026, 5:56 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://codeflow.asia/v1Sep 12, 2026, 5:35 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gatecheap.vn/v1Sep 12, 2026, 5:00 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://agonizing-reflex-darkened.ngrok-free.dev/v1Sep 12, 2026, 4:01 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ofox.io/v1Sep 12, 2026, 7:52 AM
- Self-claimed model
- openai/gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://bizdecipher.com/v1Sep 12, 2026, 7:02 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- meta
- V3 best match
- —
- Verdict
- Family mismatch
https://api.tecvesc.com/v1Sep 11, 2026, 2:22 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://claude.hanzilla.co/v1Sep 11, 2026, 2:54 AM
- Self-claimed model
- gpt-5.5
- 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 gpt55. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.