Model profile
Glm 5.1
Evidence summary
Glm 5.1 has an estimated overall rank of #101; its 90% source-sensitivity interval is #47–#219. Its behavior-only rank is #91; company governance moves the combined estimate to #101. Published evidence spans 18 evals and 6 of 7 behavior components. Its strongest relative result is DystopiaBench (baudrillard_score, #3 of 50); its weakest is ToolPrivacyBench (public_mt_poi, #9 of 9).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗glm-5-1
- Hugging Face ↗zai-org/GLM-5.1
- OpenRouter ↗z-ai/glm-5.1
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #20 / 327 | ↓0.2995 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #74 / 112 | ↑1426.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #63 / 106 | ↑0.2 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #23 / 44 | ↓75.8 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #39 / 49 | ↓89 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #30 / 50 | ↓58.5 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #21 / 46 | ↓86.7 | Source ↗official | |
| CAIS Risk Indexmask | #21 / 52 | ↓15.8 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #40 / 49 | ↓22 | Source ↗official | |
| DystopiaBenchbasaglia_score | #6 / 50 | ↓28.23 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #3 / 50 | ↓26.03 | Source ↗official | |
| DystopiaBenchhuxley_score | #5 / 50 | ↓18.7 | Source ↗official | |
| DystopiaBenchlaguardia_score | #9 / 50 | ↓40.7 | Source ↗official | |
| DystopiaBenchorwell_score | #7 / 50 | ↓26.77 | Source ↗official | |
| DystopiaBenchpetrov_score | #7 / 50 | ↓37.4 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #64 / 241 | ↑23.51 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #203 / 241 | ↑79 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #46 / 241 | ↑91.11 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #135 / 239 | ↑95.64 | Source ↗official | |
| Governance Decay under Passive Context Compactiongovernance_retention_score | #1 / 7 | ↑100 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #21 / 50 | ↓86.7 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #14 / 31 | ↓8.3 | Source ↗self run | |
| ODCV-Benchaverage_severity | #3 / 12 | ↓0.9187 | Source ↗official | |
| ODCV-Benchmisalignment_rate | #4 / 12 | ↓25 | Source ↗official | |
| SM-Benchadversarial | #9 / 78 | ↑88.29 | Source ↗official | |
| SM-Benchambiguous_interpretation | #11 / 78 | ↑90.77 | Source ↗official | |
| SM-Benchanti_hallucination | #50 / 78 | ↑88.48 | Source ↗official | |
| SM-Bencheq_boundaries | #10 / 78 | ↑73.88 | Source ↗official | |
| SM-Benchoverfit | #32 / 78 | ↑77.6 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #18 / 105 | ↑6.98 | Source ↗official | |
| SpeciEvalland_animal_4ns | #71 / 105 | ↓4.72 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #30 / 105 | ↓4.62 | Source ↗official | |
| SpeciEvalspeciesism | #63 / 105 | ↓2.12 | Source ↗official | |
| TACbase_welfare_rate | #67 / 74 | ↑17.95 | Source ↗self run | |
| ToolPrivacyBenchprivate_mt_poi | #9 / 9 | ↓28.04 | Source ↗official | |
| ToolPrivacyBenchpublic_mt_poi | #9 / 9 | ↓22.56 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.
UGI Political Values
CCPBench political narrative alignment
| Dimension | Value | Distribution |
|---|---|---|
| CCP-narrative alignment — all questions | 3.16 | |
| CCP-narrative alignment — China topics | 3.84 | |
| CCP-narrative alignment — non-China controls | 1.12 |
Agent-ValueBench Moral Foundations (MFT08)
Agent-ValueBench HEXACO
| Dimension | Value | Distribution |
|---|---|---|
| Openness to experience | 6.9 | |
| Honesty-humility | 6.6 | |
| Extraversion | 6.4 | |
| Agreeableness | 6.3 | |
| Conscientiousness | 7.6 |