← Back to model

glm53flash · Model identity and integrity report

Last updated：Aug 27, 2026, 12:20 PM · Data window: past 90 days

Measured results (90 days)

7 runs · 5 hosts · 7 anomalies

Family-fingerprint consistency

  zhipu            7  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → z-ai/glm-5                               4 (57%) ⚠ mismatch sim=0.65
  → abstain                                  3 (43%) — low confidence

Capability score distribution (auxiliary)

  0-49     ███████████░░░░░░░░░░░░░░    3
  50-69    ████░░░░░░░░░░░░░░░░░░░░░    1
  70-89    ███████████░░░░░░░░░░░░░░    3
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://free.empero.org/v1	2	0	0%	z-ai/glm-5 (1)
https://api.inferhub.dev/v1	2	77	0%	z-ai/glm-5 (2)
https://ai.input.im/v1	1	55	0%	—
https://api.tokenrouter.com/v1	1	0	0%	z-ai/glm-5 (1)
https://concepts-music-noon-downloaded.trycloudflare.com/v1	1	75	0%	—

Recent anomalies

https://free.empero.org/v1Aug 27, 2026, 9:51 AM

Self-claimed model: glm-5.3-flash
V2 predicted family: zhipu
V3 best match: —
Verdict: Full swap

https://ai.input.im/v1Aug 27, 2026, 6:20 AM

Self-claimed model: glm-5.3-flash
V2 predicted family: zhipu
V3 best match: —
Verdict: Full swap

https://api.inferhub.dev/v1Aug 27, 2026, 5:40 AM

Self-claimed model: zai/glm-5.3-flash
V2 predicted family: zhipu
V3 best match: z-ai/glm-5 (sim 0.60)
Verdict: Full swap

https://api.inferhub.dev/v1Aug 27, 2026, 5:39 AM

Self-claimed model: cbcn/glm-5.3-flash
V2 predicted family: zhipu
V3 best match: z-ai/glm-5 (sim 0.61)
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 27, 2026, 1:54 AM

Self-claimed model: z-ai/glm-5.3-flash
V2 predicted family: zhipu
V3 best match: z-ai/glm-5 (sim 0.60)
Verdict: Full swap

https://free.empero.org/v1Aug 27, 2026, 1:45 AM

Self-claimed model: glm-5.3-flash
V2 predicted family: zhipu
V3 best match: z-ai/glm-5 (sim 0.77)
Verdict: Full swap

https://concepts-music-noon-downloaded.trycloudflare.com/v1Aug 26, 2026, 7:40 PM

Self-claimed model: glm-5.3-flash
V2 predicted family: zhipu
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 glm53flash. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →