Model profile
Glm 4.6
Evidence summary
Glm 4.6 has an estimated overall rank of #153; its 90% source-sensitivity interval is #80–#258. Its behavior-only rank is #151; company governance moves the combined estimate to #153. Published evidence spans 8 evals and 6 of 7 behavior components. Its strongest relative result is SpeciEval (speciesism, #11 of 105); its weakest is AgentDrive Safety Compliance (scr, #46 of 48).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗glm-4-6
- Hugging Face ↗zai-org/GLM-4.6
- OpenRouter ↗z-ai/glm-4.6
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 | #98 / 327 | ↓0.6757 | Source ↗official | |
| AgentDrive Safety Compliancescr | #46 / 48 | ↑41.25 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #31 / 112 | ↑1449.0 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #173 / 241 | ↑12.66 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #218 / 241 | ↑74.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #160 / 241 | ↑55 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #142 / 239 | ↑95.45 | Source ↗official | |
| LiveSecBenchethics | #27 / 43 | ↑36.13 | Source ↗official | |
| LiveSecBenchfactuality | #14 / 43 | ↑58.59 | Source ↗official | |
| LiveSecBenchlegality | #26 / 43 | ↑39.39 | Source ↗official | |
| LiveSecBenchprivacy | #33 / 43 | ↑29.92 | Source ↗official | |
| LiveSecBenchpsychological_health | #15 / 43 | ↑60.3 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #53 / 105 | ↑6.8 | Source ↗official | |
| SpeciEvalland_animal_4ns | #67 / 105 | ↓4.67 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #75 / 105 | ↓4.92 | Source ↗official | |
| SpeciEvalspeciesism | #11 / 105 | ↓1.43 | Source ↗official | |
| TrustLLM contemporary collapsed applicationtrustllm | #3 / 8 | ↑0.62 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #47 / 94 | ↑90.5 | 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.