← Back to model

glm53 · Model identity and integrity report

Name: glm53 relay integrity probe aggregate
Creator: BazaarLink

Last updated：Aug 14, 2026, 1:20 PM · Data window: past 90 days

Measured results (90 days)

7 runs · 2 hosts · 7 anomalies

Family-fingerprint consistency

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

Observed V3 sub-model mapping

  → abstain                                  6 (86%) — low confidence
  → z-ai/glm-5                               1 (14%) ⚠ mismatch sim=0.60

Capability score distribution (auxiliary)

  0-49     ██████████████████░░░░░░░    5
  50-69    ███████░░░░░░░░░░░░░░░░░░    2
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://api.amanai.dev/v1	5	26	0%	—
https://api.cosmoshub.tech/v1	2	0	0%	z-ai/glm-5 (1)

Recent anomalies

https://api.cosmoshub.tech/v1Aug 14, 2026, 12:14 PM

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

https://api.amanai.dev/v1Aug 14, 2026, 12:12 PM

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

https://api.amanai.dev/v1Aug 14, 2026, 12:06 PM

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

https://api.cosmoshub.tech/v1Aug 14, 2026, 11:52 AM

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

https://api.amanai.dev/v1Aug 14, 2026, 7:57 AM

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

https://api.amanai.dev/v1Aug 14, 2026, 6:54 AM

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

https://api.amanai.dev/v1Aug 14, 2026, 5:58 AM

Self-claimed model: amanai/glm-5.3
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 glm53. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →