← Back to model

mercury25 · Model identity and integrity report

Last updated：Sep 21, 2026, 4:30 AM · Data window: past 90 days

Measured results (90 days)

5 runs · 1 hosts · 5 anomalies

Family-fingerprint consistency

  google           4  ████████████████████░░░░░   80% (suspicious)
  openai           1  █████░░░░░░░░░░░░░░░░░░░░   20% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  5 (100%) — low confidence

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.inceptionlabs.ai/v1	5	0	0%	—

Recent anomalies

https://api.inceptionlabs.ai/v1Sep 21, 2026, 3:26 AM

Self-claimed model: mercury-2.5
V2 predicted family: google
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.inceptionlabs.ai/v1Sep 17, 2026, 11:39 AM

Self-claimed model: mercury-2.5
V2 predicted family: google
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.inceptionlabs.ai/v1Sep 17, 2026, 10:22 AM

Self-claimed model: mercury-2.5
V2 predicted family: google
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.inceptionlabs.ai/v1Sep 15, 2026, 7:00 AM

Self-claimed model: mercury-2.5
V2 predicted family: google
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.inceptionlabs.ai/v1Sep 14, 2026, 4:38 PM

Self-claimed model: mercury-2.5
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming mercury25. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →