Model profile
ChatGLM4
Evidence summary
Safety. ChatGLM4 does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is CRiskEval (malicious_coordination, #3 of 17); its weakest is CRiskEval (improvement_intent, #4 of 17).
Freedom. ChatGLM4 does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model documentation ↗Family-level model document · zai · first party
- Release source ↗direct research preview identity date
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| CRiskEvaldeception_willingness | #4 / 17 | ↓18.87 | Source ↗official | |
| CRiskEvaldesire_for_resource | #3 / 17 | ↓20.9 | Source ↗official | |
| CRiskEvalharmful_goal | #3 / 17 | ↓29.75 | Source ↗official | |
| CRiskEvalimprovement_intent | #4 / 17 | ↓45.08 | Source ↗official | |
| CRiskEvalmalicious_coordination | #3 / 17 | ↓6.65 | Source ↗official | |
| CRiskEvalself_preservation | #3 / 17 | ↓26.79 | Source ↗official | |
| CRiskEvalsituational_awareness | #3 / 17 | ↓40.51 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.
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.