Model profile
GLM 5V Turbo
Evidence summary
Safety. GLM 5V Turbo does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 1 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #123 of 345); its weakest is Arena Factuality — Text Arena (factuality-only weighting) (factuality_bt_rating, #78 of 111).
Freedom. GLM 5V Turbo has an estimated Freedom rank of #430; its 90% source-sensitivity interval is #293–#508. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SpeechMap model completion (complete_pct, #95 of 181); its weakest is SpeechMap model completion (complete_pct, #95 of 181).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗glm-5v-turbo
- OpenRouter ↗z-ai/glm-5v-turbo
- Official model documentation ↗Family-level model document · zai · first party
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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #123 / 345 | ↓0.688 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #78 / 111 | ↑1422.0 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| SpeechMap model completioncomplete_pct | #95 / 181 | ↑56.9 | Source ↗official |