Model profile
Glm 4.5
Evidence summary
Glm 4.5 has an estimated overall rank of #199; its 90% source-sensitivity interval is #63–#263. Its behavior-only rank is #190; company governance moves the combined estimate to #199. Published evidence spans 9 evals and 7 of 7 behavior components. Its strongest relative result is Confabulations (confabulation_rate, #8 of 52); its weakest is FlagEval Safety and Values (a1_qualified_rate, #18 of 18).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗glm-4.5
- Hugging Face ↗zai-org/GLM-4.5
- OpenRouter ↗z-ai/glm-4.5
- 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 | #110 / 328 | ↓0.7015 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #94 / 106 | ↑0.07 | Source ↗official | |
| Confabulationsconfabulation_rate | #8 / 52 | ↓7.921 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #46 / 241 | ↑30.49 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #209 / 241 | ↑77.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #172 / 241 | ↑52.22 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #134 / 239 | ↑95.76 | Source ↗official | |
| FlagEval Safety and Valuesa1_qualified_rate | #18 / 18 | ↑59.1 | Source ↗official | |
| FlagEval Safety and Valuesa2_qualified_rate | #18 / 18 | ↑57.84 | Source ↗official | |
| FlagEval Safety and Valuesa3_qualified_rate | #18 / 18 | ↑60.32 | Source ↗official | |
| FlagEval Safety and Valuesa4_qualified_rate | #18 / 18 | ↑60.7 | Source ↗official | |
| FlagEval Safety and Valuesa5_qualified_rate | #17 / 18 | ↑56.79 | Source ↗official | |
| FORTRESSaverage_risk_score | #44 / 49 | ↓59.58 | Source ↗official | |
| FORTRESSover_refusal_score | #15 / 46 | ↓2.54 | Source ↗official | |
| MASKlying_probability_pct | #25 / 53 | ↓38.54 | Source ↗official | |
| Social Welfare Function Benchmarkfairness | #13 / 19 | ↑0.475 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #69 / 113 | ↑6.7 | Source ↗official | |
| SpeciEvalland_animal_4ns | #49 / 113 | ↓4.47 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #98 / 113 | ↓5.09 | Source ↗official | |
| SpeciEvalspeciesism | #23 / 113 | ↓1.58 | 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.