qwen38flash · Model identity and integrity report
Last updated：Sep 1, 2026, 1:50 PM · Data window: past 90 days
Measured results (90 days)
5 runs · 3 hosts · 3 anomalies
Family-fingerprint consistency
qwen 3 ███████████████░░░░░░░░░░ 60% (suspicious) unknown 2 ██████████░░░░░░░░░░░░░░░ 40% (suspicious)
Observed V3 sub-model mapping
→ abstain 3 (60%) — low confidence → unknown 2 (40%) ⚠ mismatch
Capability score distribution (auxiliary)
0-49 ████████████████████░░░░░ 4 50-69 █████░░░░░░░░░░░░░░░░░░░░ 1 70-89 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.b.ai/v1 | 3 | 22 | 0% | — |
| https://sharellm.cn/v1 | 1 | 0 | 0% | — |
| http://bore.pub:28138/v1 | 1 | 16 | 0% | — |
Recent anomalies
http://bore.pub:28138/v1Aug 31, 2026, 10:23 AM
- Self-claimed model
- am/qwen3.8-flash
- V2 predicted family
- qwen
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.b.ai/v1Aug 30, 2026, 6:49 PM
- Self-claimed model
- qwen3.8-flash
- V2 predicted family
- qwen
- V3 best match
- —
- Verdict
- Family mismatch
https://api.b.ai/v1Aug 29, 2026, 7:03 AM
- Self-claimed model
- qwen3.8-flash
- V2 predicted family
- qwen
- V3 best match
- —
- 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 qwen38flash. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.