openai/gpt-5.2 · Model identity and integrity report
Last updated：Jul 30, 2026, 12:54 PM · Data window: past 90 days
Verification capability — fingerprint reference available
- Family
- openai
- V3 sub-model reference
- Available ✓
- Checks
- 知識截止 · 能力探針 · 拒絕模板 · 拒絕溫度參數
- Family-fingerprint coverage
- 52 weighted rules · 8 feature categories
Concrete reference answers, refusal templates, and individual signal weights are not published because disclosure would help spoofing endpoints evade detection.
Measured results (90 days)
24 runs · 16 hosts · 10 anomalies
Family-fingerprint consistency
openai 17 ██████████████████░░░░░░░ 71% (expected) unknown 5 █████░░░░░░░░░░░░░░░░░░░░ 21% (suspicious) anthropic 2 ██░░░░░░░░░░░░░░░░░░░░░░░ 8% (suspicious)
Observed V3 sub-model mapping
→ openai/gpt-5.2 9 (38%) ✓ correct sim=0.98 → abstain 7 (29%) — low confidence → unknown 5 (21%) ⚠ mismatch → openai/gpt-5.4-mini 3 (13%) ⚠ mismatch sim=0.76
Capability score distribution (auxiliary)
0-49 █████████████░░░░░░░░░░░░ 12 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 1 70-89 ██░░░░░░░░░░░░░░░░░░░░░░░ 2 90-100 ██████████░░░░░░░░░░░░░░░ 9
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://www.moyu.info/v1 | 6 | 91 | 100% | openai/gpt-5.4-mini (3) |
| https://llm-api.net/v1 | 2 | 0 | 50% | — |
| https://codex.hiyo.top/v1 | 2 | 0 | 0% | — |
| https://api.quotaflow.ai/openai/v1 | 2 | 72 | 50% | openai/gpt-5.2 (1) |
| https://vip.j3gb.com/v1 | 1 | 0 | 100% | — |
| https://omaleai.qzz.io/v1 | 1 | 39 | 0% | — |
| http://api.halphen.cn/openai/v1 | 1 | 0 | 0% | — |
| https://lumibest.cc/v1 | 1 | 0 | 100% | openai/gpt-5.2 (1) |
| https://ai98pro.xyz/v1 | 1 | 92 | 0% | — |
| https://yunwu.ai/v1 | 1 | 94 | 100% | openai/gpt-5.2 (1) |
| https://ai.websee.top/v1 | 1 | 0 | 100% | openai/gpt-5.2 (1) |
| https://www.daydreaming.work/v1 | 1 | 95 | 100% | openai/gpt-5.2 (1) |
| https://dragoncode.codes/v1 | 1 | 0 | 100% | openai/gpt-5.2 (1) |
| https://sub2.clouddiskdownload.top/v1 | 1 | 0 | 100% | openai/gpt-5.2 (1) |
| https://openai.chumeng.plus/v1 | 1 | 0 | 100% | openai/gpt-5.2 (1) |
| https://api.hustai.uk/v1 | 1 | 91 | 100% | — |
Recent anomalies
https://llm-api.net/v1Jul 22, 2026, 2:33 PM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://llm-api.net/v1Jul 22, 2026, 2:11 PM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vip.j3gb.com/v1Jul 9, 2026, 11:23 AM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
http://api.halphen.cn/openai/v1Jun 16, 2026, 3:51 AM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.moyu.info/v1May 26, 2026, 5:27 PM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4-mini (sim 0.75)
- Verdict
- Sub-model downgrade
https://www.moyu.info/v1May 22, 2026, 8:31 AM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.moyu.info/v1May 22, 2026, 8:20 AM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4-mini (sim 0.75)
- Verdict
- Sub-model downgrade
https://www.moyu.info/v1May 22, 2026, 8:05 AM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.moyu.info/v1May 22, 2026, 7:24 AM
- Self-claimed model
- gpt-5.2
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4-mini (sim 0.80)
- Verdict
- Sub-model downgrade
https://api.hustai.uk/v1May 3, 2026, 11:38 AM
- Self-claimed model
- gpt-5.2
- 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 openai/gpt-5.2. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.