minimaxm25 · Model identity and integrity report
Last updated：Sep 13, 2026, 6:44 PM · Data window: past 90 days
Measured results (90 days)
7 runs · 5 hosts · 6 anomalies
Family-fingerprint consistency
openai 6 ██████████████████████░░░ 86% (suspicious) unknown 1 ████░░░░░░░░░░░░░░░░░░░░░ 14% (suspicious)
Observed V3 sub-model mapping
→ abstain 3 (43%) — low confidence → unknown 2 (29%) ⚠ mismatch → openai/gpt-4.1 2 (29%) ⚠ mismatch sim=0.74
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://dashscope.aliyuncs.com/compatible-mode/v1 | 3 | 0 | 0% | openai/gpt-4.1 (2) |
| https://serverless.tensormesh.ai/v1 | 1 | 0 | 0% | — |
| https://ai.kscsnkli.site/v1 | 1 | 37 | 0% | — |
| https://token.ynai.cloudhubportal.com/v1 | 1 | 42 | 0% | — |
| https://api.uglycat.cc/v1 | 1 | 0 | 0% | — |
Recent anomalies
https://serverless.tensormesh.ai/v1Aug 26, 2026, 10:00 PM
- Self-claimed model
- MiniMaxAI/MiniMax-M2.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ai.kscsnkli.site/v1Aug 24, 2026, 10:05 AM
- Self-claimed model
- MiniMax-M2.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://token.ynai.cloudhubportal.com/v1Jul 30, 2026, 5:35 PM
- Self-claimed model
- MiniMax-M2.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://dashscope.aliyuncs.com/compatible-mode/v1Jul 26, 2026, 11:49 AM
- Self-claimed model
- MiniMax-M2.5
- V2 predicted family
- openai
- V3 best match
- openai/gpt-4.1 (sim 0.74)
- Verdict
- Full swap
https://dashscope.aliyuncs.com/compatible-mode/v1Jul 25, 2026, 7:00 PM
- Self-claimed model
- MiniMax-M2.5
- V2 predicted family
- openai
- V3 best match
- openai/gpt-4.1 (sim 0.74)
- Verdict
- Full swap
https://api.uglycat.cc/v1Jun 28, 2026, 1:13 PM
- Self-claimed model
- minimax-m2.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- Family mismatch
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming minimaxm25. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.