claudesonnet46thinking · Model identity and integrity report
Last updated：Sep 13, 2026, 9:22 PM · Data window: past 90 days
Measured results (90 days)
10 runs · 7 hosts · 8 anomalies
Family-fingerprint consistency
anthropic 8 ████████████████████░░░░░ 80% (suspicious) unknown 2 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious)
Observed V3 sub-model mapping
→ abstain 6 (60%) — low confidence → unknown 3 (30%) ⚠ mismatch → anthropic/claude-haiku-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://emtf.aipm9527.online/v1 | 3 | 58 | 0% | — |
| https://api.xcdw.us/v1 | 2 | 76 | 0% | — |
| https://api.jumengai.net/v1 | 1 | 72 | 0% | — |
| https://api.ciciapi.com/v1 | 1 | 0 | 0% | anthropic/claude-haiku-4.5 (1) |
| https://api.lmuai.com/v1 | 1 | 0 | 0% | — |
| https://freeapi.s3.fan/v1 | 1 | 8 | 0% | — |
| https://xiaomuai.cn/v1 | 1 | 0 | 0% | — |
Recent anomalies
https://emtf.aipm9527.online/v1Aug 9, 2026, 2:10 AM
- Self-claimed model
- anthropic/claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://emtf.aipm9527.online/v1Aug 3, 2026, 4:32 AM
- Self-claimed model
- anthropic/claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://api.jumengai.net/v1Jul 26, 2026, 5:17 PM
- Self-claimed model
- 【K】claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ciciapi.com/v1Jun 30, 2026, 8:07 AM
- Self-claimed model
- claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.72)
- Verdict
- Full swap
https://api.xcdw.us/v1Jun 24, 2026, 8:12 PM
- Self-claimed model
- claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.lmuai.com/v1Jun 23, 2026, 2:05 PM
- Self-claimed model
- claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.xcdw.us/v1Jun 20, 2026, 12:39 PM
- Self-claimed model
- claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://xiaomuai.cn/v1Jun 17, 2026, 2:04 AM
- Self-claimed model
- claude-sonnet-4-6-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming claudesonnet46thinking. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.