deepseek/deepseek-v3.2 · Model identity and integrity report
Last updated：Jul 30, 2026, 3:15 PM · Data window: past 90 days
Verification capability — fingerprint reference available
- Family
- deepseek
- V3 sub-model reference
- Available ✓
- Checks
- 知識截止 · 能力探針 · 拒絕模板 · 拒絕溫度參數
- Family-fingerprint coverage
- 7 weighted rules · 4 feature categories
Concrete reference answers, refusal templates, and individual signal weights are not published because disclosure would help spoofing endpoints evade detection.
Measured results (90 days)
2 runs · 2 hosts · 1 anomalies
Family-fingerprint consistency
deepseek 1 █████████████░░░░░░░░░░░░ 50% (expected) openai 1 █████████████░░░░░░░░░░░░ 50% (suspicious)
Observed V3 sub-model mapping
→ deepseek/deepseek-v3.2 1 (50%) ✓ correct sim=0.77 → abstain 1 (50%) — low confidence
Capability score distribution (auxiliary)
0-49 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 █████████████████████████ 2 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.ikun.cloud-ip.cc/v1 | 1 | 72 | 100% | deepseek/deepseek-v3.2 (1) |
| https://www.moyu.info/v1 | 1 | 72 | 0% | — |
Recent anomalies
https://www.moyu.info/v1May 5, 2026, 1:22 PM
- Self-claimed model
- deepseek-v3.2
- 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 deepseek/deepseek-v3.2. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.