claudemythospreview · Model identity and integrity report
Last updated：Sep 11, 2026, 12:51 PM · Data window: past 90 days
Measured results (90 days)
5 runs · 2 hosts · 4 anomalies
Family-fingerprint consistency
anthropic 3 ███████████████░░░░░░░░░░ 60% (suspicious) openai 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious) unknown 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious)
Observed V3 sub-model mapping
→ abstain 3 (60%) — low confidence → unknown 1 (20%) ⚠ mismatch → anthropic/claude-sonnet-4.6 1 (20%) ⚠ mismatch sim=0.76
Capability score distribution (auxiliary)
0-49 █████████████████████████ 5 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://codecraftapi.com/v1 | 4 | 0 | 0% | — |
| https://api.huanxu.one/v1 | 1 | 0 | 0% | anthropic/claude-sonnet-4.6 (1) |
Recent anomalies
https://codecraftapi.com/v1Sep 9, 2026, 11:14 AM
- Self-claimed model
- claude-mythos-preview
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://codecraftapi.com/v1Sep 9, 2026, 10:15 AM
- Self-claimed model
- claude-mythos-preview
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://codecraftapi.com/v1Sep 7, 2026, 3:00 AM
- Self-claimed model
- claude-mythos-preview
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.huanxu.one/v1Jul 6, 2026, 11:22 AM
- Self-claimed model
- claude-mythos-preview
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-sonnet-4.6 (sim 0.76)
- Verdict
- Full swap
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming claudemythospreview. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.