grok · Model identity and integrity report
Last updated：Aug 30, 2026, 7:00 AM · Data window: past 90 days
Measured results (90 days)
5 runs · 4 hosts · 4 anomalies
Family-fingerprint consistency
anthropic 3 ███████████████░░░░░░░░░░ 60% (suspicious) unknown 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious) openai 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious)
Observed V3 sub-model mapping
→ abstain 3 (60%) — low confidence → unknown 1 (20%) ⚠ mismatch → openai/gpt-5 1 (20%) ⚠ mismatch sim=0.82
Capability score distribution (auxiliary)
0-49 ████████████████████░░░░░ 4 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 █████░░░░░░░░░░░░░░░░░░░░ 1 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.srbyte.dev/v1 | 2 | 37 | 0% | — |
| https://router.srbyte.dev/v1 | 1 | 0 | 0% | — |
| https://xfmcp.com:10110/v1 | 1 | 0 | 0% | — |
| https://mzeapi.top/v1 | 1 | 0 | 0% | openai/gpt-5 (1) |
Recent anomalies
https://router.srbyte.dev/v1Aug 30, 2026, 5:56 AM
- Self-claimed model
- grok
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.srbyte.dev/v1Aug 29, 2026, 9:14 AM
- Self-claimed model
- grok
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.srbyte.dev/v1Aug 28, 2026, 4:50 AM
- Self-claimed model
- grok
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://mzeapi.top/v1Jul 22, 2026, 12:54 PM
- Self-claimed model
- grok
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5 (sim 0.82)
- 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 grok. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.