arcee-ai/trinity-large-thinking · Model identity and integrity report

Last updated：Sep 13, 2026, 9:22 PM · Data window: past 90 days

Measured results (90 days)

1 runs · 1 hosts · 1 anomalies

Family-fingerprint consistency

  anthropic        1  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → anthropic/claude-sonnet-5                1 (100%) ⚠ mismatch sim=0.60

Capability score distribution (auxiliary)

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

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://api.blackbox.ai/v1	1	61	0%	anthropic/claude-sonnet-5 (1)

Recent anomalies

https://api.blackbox.ai/v1Aug 6, 2026, 2:49 PM

Self-claimed model: blackboxai/arcee-ai/trinity-large-thinking
V2 predicted family: anthropic
V3 best match: anthropic/claude-sonnet-5 (sim 0.60)
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 arcee-ai/trinity-large-thinking. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →