46opus · Model identity and integrity report

Name: 46opus relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 12:42 PM · Data window: past 90 days

Measured results (90 days)

7 runs · 2 hosts · 6 anomalies

Family-fingerprint consistency

  anthropic        5  ██████████████████░░░░░░░   71% (suspicious)
  unknown          1  ████░░░░░░░░░░░░░░░░░░░░░   14% (suspicious)
  openai           1  ████░░░░░░░░░░░░░░░░░░░░░   14% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  2 (29%) — low confidence
  → unknown                                  2 (29%) ⚠ mismatch
  → anthropic/claude-opus-4.6                1 (14%) ⚠ mismatch sim=0.84
  → anthropic/claude-sonnet-4.6              1 (14%) ⚠ mismatch sim=0.82
  → anthropic/claude-haiku-4.5               1 (14%) ⚠ mismatch sim=0.81

Capability score distribution (auxiliary)

  0-49     █████████████████████████    7
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://stoneai.fun/v1	4	0	0%	anthropic/claude-sonnet-4.6 (1)
https://www.stoneai.fun/v1	3	0	0%	anthropic/claude-opus-4.6 (1)

Recent anomalies

https://www.stoneai.fun/v1May 12, 2026, 1:00 AM

Self-claimed model: 雪松-克4.6-opus
V2 predicted family: anthropic
V3 best match: anthropic/claude-opus-4.6 (sim 0.84)
Verdict: Full swap

https://www.stoneai.fun/v1May 11, 2026, 6:25 AM

Self-claimed model: 玉兰-克4.6-opus
V2 predicted family: anthropic
V3 best match: —
Verdict: Family mismatch

https://www.stoneai.fun/v1May 11, 2026, 1:35 AM

Self-claimed model: 雪松-克4.6-opus
V2 predicted family: anthropic
V3 best match: —
Verdict: Family mismatch

https://stoneai.fun/v1May 10, 2026, 1:08 PM

Self-claimed model: 星棠-克4.6-opus
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://stoneai.fun/v1May 8, 2026, 3:46 PM

Self-claimed model: 雪松-克4.6-opus
V2 predicted family: anthropic
V3 best match: anthropic/claude-sonnet-4.6 (sim 0.82)
Verdict: Full swap

https://stoneai.fun/v1May 8, 2026, 3:43 PM

Self-claimed model: 玉兰-克4.6-opus
V2 predicted family: anthropic
V3 best match: anthropic/claude-haiku-4.5 (sim 0.81)
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 46opus. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →