Model profile
Glm 5 Turbo
Z.aideveloper
2026-03-15release date
#227 / 312overall rank
5eval lineages
Evidence summary
Glm 5 Turbo has an estimated overall rank of #227; its 90% source-sensitivity interval is #110–#287. Its behavior-only rank is #222; company governance moves the combined estimate to #227. Published evidence spans 5 evals and 5 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #51 of 241); its weakest is SM-Bench (ambiguous_interpretation, #79 of 79).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗glm-5-turbo
- OpenRouter ↗z-ai/glm-5-turbo
- Official model documentation ↗Family-level model document · zai · first party
- Release source ↗curated outward evidence
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 | #84 / 330 | ↓0.6264 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #55 / 106 | ↑0.27 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #187 / 241 | ↑11.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #213 / 241 | ↑76 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #51 / 241 | ↑88.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #142 / 239 | ↑95.45 | Source ↗official | |
| SM-Benchadversarial | #63 / 79 | ↑77.56 | Source ↗official | |
| SM-Benchambiguous_interpretation | #79 / 79 | ↑13.69 | Source ↗official | |
| SM-Benchanti_hallucination | #79 / 79 | ↑18.85 | Source ↗official | |
| SM-Bencheq_boundaries | #20 / 79 | ↑69.1 | Source ↗official | |
| SM-Benchoverfit | #42 / 79 | ↑70.49 | Source ↗official | |
| WildClawBench Safety & Alignment (OpenClaw harness)safety_alignment_score_pct | #21 / 24 | ↑32.19 | Source ↗official |