kimik25 · Model identity and integrity report
Last updated：Aug 27, 2026, 3:39 PM · Data window: past 90 days
Measured results (90 days)
4 runs · 3 hosts · 3 anomalies
Family-fingerprint consistency
anthropic 3 ███████████████████░░░░░░ 75% (suspicious) unknown 1 ██████░░░░░░░░░░░░░░░░░░░ 25% (suspicious)
Observed V3 sub-model mapping
→ abstain 3 (75%) — low confidence → unknown 1 (25%) ⚠ mismatch
Capability score distribution (auxiliary)
0-49 ███████████████████░░░░░░ 3 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 ██████░░░░░░░░░░░░░░░░░░░ 1 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://tokenus.net/v1 | 2 | 35 | 0% | — |
| https://aiapi.syuan.org/v1 | 1 | 0 | 0% | — |
| https://baipiao.dbgai.xyz/v1 | 1 | 26 | 0% | — |
Recent anomalies
https://aiapi.syuan.org/v1Aug 15, 2026, 9:32 PM
- Self-claimed model
- kimi-k2.5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://tokenus.net/v1Aug 15, 2026, 1:01 PM
- Self-claimed model
- kimi-k2.5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://tokenus.net/v1Aug 12, 2026, 10:02 AM
- Self-claimed model
- kimi-k2.5
- 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 kimik25. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.