← Back to model

qwen38max · Model identity and integrity report

Name: qwen38max relay integrity probe aggregate
Creator: BazaarLink

Last updated：Aug 11, 2026, 7:02 PM · Data window: past 90 days

Measured results (90 days)

5 runs · 4 hosts · 5 anomalies

Family-fingerprint consistency

  qwen             4  ████████████████████░░░░░   80% (suspicious)
  anthropic        1  █████░░░░░░░░░░░░░░░░░░░░   20% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  4 (80%) — low confidence
  → qwen/qwen3-next-80b-a3b-instruct         1 (20%) ⚠ mismatch sim=0.61

Capability score distribution (auxiliary)

  0-49     ███████████████░░░░░░░░░░    3
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ██████████░░░░░░░░░░░░░░░    2
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://ai.kaiplay.my.id/v1	2	82	0%	qwen/qwen3-next-80b-a3b-instruct (1)
https://dashscope.aliyuncs.com/compatible-mode/v1	1	0	0%	—
https://api.tokenrouter.com/v1	1	0	0%	—
https://llm.xinlicloud.top/v1	1	36	0%	—

Recent anomalies

https://dashscope.aliyuncs.com/compatible-mode/v1Aug 11, 2026, 6:00 PM

Self-claimed model: qwen3.8-max
V2 predicted family: qwen
V3 best match: —
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 11, 2026, 9:27 AM

Self-claimed model: qwen/qwen3.8-max
V2 predicted family: qwen
V3 best match: —
Verdict: Full swap

https://ai.kaiplay.my.id/v1Aug 9, 2026, 11:37 AM

Self-claimed model: qd/qwen3.8-max
V2 predicted family: qwen
V3 best match: qwen/qwen3-next-80b-a3b-instruct (sim 0.61)
Verdict: Full swap

https://llm.xinlicloud.top/v1Aug 9, 2026, 7:04 AM

Self-claimed model: qwen3.8-max
V2 predicted family: qwen
V3 best match: —
Verdict: Family mismatch

https://ai.kaiplay.my.id/v1Aug 9, 2026, 4:36 AM

Self-claimed model: qd/qwen3.8-max
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 qwen38max. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →