models · Model identity and integrity report
Last updated：Sep 26, 2026, 11:45 AM · Data window: past 90 days
Measured results (90 days)
10 runs · 3 hosts · 10 anomalies
Family-fingerprint consistency
anthropic 10 █████████████████████████ 100% (suspicious)
Observed V3 sub-model mapping
→ abstain 9 (90%) — low confidence → anthropic/claude-opus-4.5 1 (10%) ⚠ mismatch sim=0.72
Capability score distribution (auxiliary)
0-49 █████████████░░░░░░░░░░░░ 5 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 █████████████░░░░░░░░░░░░ 5 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://sotamodel.net/v1 | 5 | 30 | 0% | — |
| https://www.sotamodel.net/v1 | 4 | 37 | 0% | anthropic/claude-opus-4.5 (1) |
| https://sd.santaa.ai/v1 | 1 | 75 | 0% | — |
Recent anomalies
https://sotamodel.net/v1Aug 30, 2026, 5:40 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.sotamodel.net/v1Aug 24, 2026, 1:46 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sotamodel.net/v1Aug 18, 2026, 3:12 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.sotamodel.net/v1Aug 12, 2026, 2:44 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sd.santaa.ai/v1Aug 11, 2026, 4:18 PM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sotamodel.net/v1Aug 10, 2026, 1:18 PM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sotamodel.net/v1Aug 10, 2026, 3:12 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sotamodel.net/v1Aug 10, 2026, 3:06 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.sotamodel.net/v1Aug 7, 2026, 9:10 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.sotamodel.net/v1Aug 7, 2026, 8:47 AM
- Self-claimed model
- model-S
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.72)
- 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 models. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.