tencent/hy3 · Model identity and integrity report
Last updated：Sep 13, 2026, 9:23 PM · Data window: past 90 days
Measured results (90 days)
13 runs · 12 hosts · 12 anomalies
Family-fingerprint consistency
anthropic 7 ██████████████░░░░░░░░░░░ 54% (suspicious) openai 4 ████████░░░░░░░░░░░░░░░░░ 31% (suspicious) unknown 1 ██░░░░░░░░░░░░░░░░░░░░░░░ 8% (suspicious) google 1 ██░░░░░░░░░░░░░░░░░░░░░░░ 8% (suspicious)
Observed V3 sub-model mapping
→ abstain 10 (77%) — low confidence → unknown 2 (15%) ⚠ mismatch → anthropic/claude-opus-4.6 1 ( 8%) ⚠ mismatch sim=0.91
Capability score distribution (auxiliary)
0-49 ███████████████████░░░░░░ 10 50-69 ██░░░░░░░░░░░░░░░░░░░░░░░ 1 70-89 ████░░░░░░░░░░░░░░░░░░░░░ 2 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.b.ai/v1 | 2 | 35 | 0% | — |
| https://cavoti.com/v1 | 1 | 0 | 0% | — |
| https://api.nbhooks.my.id/v1 | 1 | 0 | 0% | — |
| https://bandelbanget.xyz/v1 | 1 | 0 | 0% | — |
| https://anti.thuxeko.io.vn/v1 | 1 | 0 | 0% | — |
| https://api.sld.lol/v1 | 1 | 0 | 0% | — |
| https://ai.autoapp.biz.id/v1 | 1 | 0 | 0% | — |
| http://bore.pub:28138/v1 | 1 | 71 | 0% | anthropic/claude-opus-4.6 (1) |
| https://pianyitoken.gay/v1 | 1 | 67 | 0% | — |
| https://griphubrouter.web.id/v1 | 1 | 0 | 0% | — |
| https://ai.unitenav.com/v1 | 1 | 5 | 0% | — |
| https://ai-api-server.miomoe.cn/v1 | 1 | 47 | 0% | — |
Recent anomalies
https://api.b.ai/v1Sep 13, 2026, 8:00 PM
- Self-claimed model
- hy3
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://cavoti.com/v1Sep 13, 2026, 1:59 PM
- Self-claimed model
- hy3
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.nbhooks.my.id/v1Sep 12, 2026, 8:05 PM
- Self-claimed model
- Gregv2/hy3
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://bandelbanget.xyz/v1Sep 9, 2026, 12:15 PM
- Self-claimed model
- hy3
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.sld.lol/v1Sep 7, 2026, 10:44 AM
- Self-claimed model
- hy3
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ai.autoapp.biz.id/v1Aug 31, 2026, 11:39 AM
- Self-claimed model
- hy3
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
http://bore.pub:28138/v1Aug 31, 2026, 11:24 AM
- Self-claimed model
- am/hy3
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.6 (sim 0.91)
- Verdict
- Full swap
https://pianyitoken.gay/v1Aug 29, 2026, 8:59 PM
- Self-claimed model
- 订阅-hy3
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://griphubrouter.web.id/v1Aug 25, 2026, 7:52 AM
- Self-claimed model
- hy3
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.b.ai/v1Aug 21, 2026, 6:55 AM
- Self-claimed model
- hy3
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ai.unitenav.com/v1Aug 12, 2026, 3:45 AM
- Self-claimed model
- hy3
- V2 predicted family
- V3 best match
- —
- Verdict
- Family mismatch
https://ai-api-server.miomoe.cn/v1Aug 8, 2026, 6:55 PM
- Self-claimed model
- hy3
- V2 predicted family
- anthropic
- 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 tencent/hy3. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.