qwen38maxpreview · Model identity and integrity report
Last updated：Sep 11, 2026, 12:52 PM · Data window: past 90 days
Measured results (90 days)
5 runs · 4 hosts · 3 anomalies
Family-fingerprint consistency
qwen 2 ██████████░░░░░░░░░░░░░░░ 40% (suspicious) unknown 2 ██████████░░░░░░░░░░░░░░░ 40% (suspicious) anthropic 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious)
Observed V3 sub-model mapping
→ abstain 2 (40%) — low confidence → unknown 2 (40%) ⚠ mismatch → qwen/qwen3-max 1 (20%) ⚠ mismatch sim=0.71
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://api.amanai.dev/v1 | 2 | 0 | 0% | — |
| https://api.ghrocx.my.id/v1 | 1 | 0 | 0% | — |
| https://api.a6api.com/v1 | 1 | 0 | 0% | — |
| https://api.cosmoshub.tech/v1 | 1 | 0 | 0% | qwen/qwen3-max (1) |
Recent anomalies
https://api.ghrocx.my.id/v1Sep 9, 2026, 9:58 AM
- Self-claimed model
- ghrocx/qwen3.8-max-preview
- V2 predicted family
- qwen
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.amanai.dev/v1Jul 31, 2026, 4:53 PM
- Self-claimed model
- amanai/qwen3.8-max-preview
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://api.cosmoshub.tech/v1Jul 27, 2026, 3:04 PM
- Self-claimed model
- qwen-3.8-max-preview
- V2 predicted family
- qwen
- V3 best match
- qwen/qwen3-max (sim 0.71)
- 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 qwen38maxpreview. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.