glm5 · Model identity and integrity report
Last updated：Sep 14, 2026, 2:19 PM · Data window: past 90 days
Verification capability — fingerprint reference available
- Family
- zhipu
- V3 sub-model reference
- Available ✓
- Checks
- 知識截止 · 能力探針 · 拒絕模板 · 拒絕溫度參數
Concrete reference answers, refusal templates, and individual signal weights are not published because disclosure would help spoofing endpoints evade detection.
Measured results (90 days)
25 runs · 19 hosts · 22 anomalies
Family-fingerprint consistency
zhipu 14 ██████████████░░░░░░░░░░░ 56% (suspicious) unknown 3 ███░░░░░░░░░░░░░░░░░░░░░░ 12% (suspicious) anthropic 3 ███░░░░░░░░░░░░░░░░░░░░░░ 12% (suspicious) openai 3 ███░░░░░░░░░░░░░░░░░░░░░░ 12% (suspicious) deepseek 1 █░░░░░░░░░░░░░░░░░░░░░░░░ 4% (suspicious) google 1 █░░░░░░░░░░░░░░░░░░░░░░░░ 4% (suspicious)
Observed V3 sub-model mapping
→ abstain 12 (48%) — low confidence → z-ai/glm-5 7 (28%) ⚠ mismatch sim=0.67 → unknown 4 (16%) ⚠ mismatch → z-ai/glm-5.2 1 ( 4%) ⚠ mismatch sim=0.75 → google/gemini-2.5-flash-lite 1 ( 4%) ⚠ mismatch sim=0.60
Capability score distribution (auxiliary)
0-49 ██████████░░░░░░░░░░░░░░░ 10 50-69 ████░░░░░░░░░░░░░░░░░░░░░ 4 70-89 ███████████░░░░░░░░░░░░░░ 11 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://ai.lnapi.cn/v1 | 5 | 83 | 0% | z-ai/glm-5 (5) |
| https://api.xkiro.com/v1 | 2 | 69 | 0% | z-ai/glm-5 (1) |
| https://api.supxh.xin/v1 | 2 | 39 | 0% | — |
| https://speed.toter.me/v1 | 1 | 0 | 0% | — |
| https://api.gutsai.id/v1 | 1 | 37 | 0% | — |
| https://wincode.winning.com.cn/ai/v1 | 1 | 0 | 0% | — |
| https://aiapi.syuan.org/v1 | 1 | 0 | 0% | z-ai/glm-5 (1) |
| https://aihub.sbyma.icu/v1 | 1 | 0 | 0% | — |
| https://enterprise.blackbox.ai/v1 | 1 | 84 | 0% | — |
| https://openrouter.ai/api/v1 | 1 | 0 | 0% | — |
| https://token.ynai.cloudhubportal.com/v1 | 1 | 68 | 0% | z-ai/glm-5.2 (1) |
| https://api.cosmoshub.tech/v1 | 1 | 0 | 0% | — |
| https://opencode.ai/zen/go/v1 | 1 | 79 | 0% | — |
| https://api.vectorengine.ai/v1 | 1 | 0 | 0% | — |
| https://mua.icyuan.xyz/v1 | 1 | 67 | 0% | — |
| https://api.futureppo.top/v1 | 1 | 51 | 0% | — |
| https://www.mofas.one/v1 | 1 | 87 | 0% | — |
| https://ai.artsapi.com/v1 | 1 | 79 | 0% | google/gemini-2.5-flash-lite (1) |
| http://47.95.120.174:8001/v1 | 1 | 0 | 0% | — |
Recent anomalies
https://speed.toter.me/v1Sep 5, 2026, 2:16 PM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- —
- Verdict
- Full swap
https://api.xkiro.com/v1Aug 31, 2026, 4:03 AM
- Self-claimed model
- z-ai/glm-5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5 (sim 0.61)
- Verdict
- Full swap
https://api.xkiro.com/v1Aug 31, 2026, 4:03 AM
- Self-claimed model
- z-ai/glm-5
- V2 predicted family
- zhipu
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://wincode.winning.com.cn/ai/v1Aug 22, 2026, 12:47 PM
- Self-claimed model
- glm-5
- V2 predicted family
- deepseek
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://aiapi.syuan.org/v1Aug 15, 2026, 9:26 PM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5 (sim 0.82)
- Verdict
- Full swap
https://enterprise.blackbox.ai/v1Aug 10, 2026, 2:36 AM
- Self-claimed model
- z-ai/glm-5
- V2 predicted family
- zhipu
- V3 best match
- —
- Verdict
- Full swap
https://openrouter.ai/api/v1Aug 6, 2026, 6:39 PM
- Self-claimed model
- z-ai/glm-5
- V2 predicted family
- zhipu
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://token.ynai.cloudhubportal.com/v1Jul 30, 2026, 5:53 PM
- Self-claimed model
- glm5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5.2 (sim 0.75)
- Verdict
- Full swap
https://api.cosmoshub.tech/v1Jul 25, 2026, 1:48 PM
- Self-claimed model
- glm-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://ai.lnapi.cn/v1Jul 8, 2026, 12:24 PM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5 (sim 0.66)
- Verdict
- Family mismatch
https://ai.lnapi.cn/v1Jul 8, 2026, 8:25 AM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5 (sim 0.68)
- Verdict
- Family mismatch
https://ai.lnapi.cn/v1Jul 8, 2026, 8:08 AM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5 (sim 0.69)
- Verdict
- Family mismatch
https://ai.lnapi.cn/v1Jul 8, 2026, 7:49 AM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5 (sim 0.63)
- Verdict
- Family mismatch
https://ai.lnapi.cn/v1Jul 8, 2026, 7:45 AM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- z-ai/glm-5 (sim 0.63)
- Verdict
- Family mismatch
https://opencode.ai/zen/go/v1Jul 1, 2026, 2:51 PM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.vectorengine.ai/v1Jul 1, 2026, 11:34 AM
- Self-claimed model
- glm-5
- V2 predicted family
- zhipu
- V3 best match
- —
- Verdict
- Family mismatch
https://api.supxh.xin/v1Jun 27, 2026, 12:02 PM
- Self-claimed model
- glm-5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://mua.icyuan.xyz/v1Jun 27, 2026, 11:32 AM
- Self-claimed model
- glm-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.supxh.xin/v1Jun 24, 2026, 11:59 PM
- Self-claimed model
- glm-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://www.mofas.one/v1Jun 22, 2026, 8:55 AM
- Self-claimed model
- glm-5
- 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 glm5. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.