← Models

Model profile

Glm 4.6

Z.aideveloper
2025-09-30release date
#123 / 267overall rank
5eval lineages

Evidence summary

Glm 4.6 has an estimated overall rank of #123; its 90% source-sensitivity interval is #63–#223. Its behavior-only rank is #121; company governance moves the combined estimate to #123. Published evidence spans 5 evals and 6 of 7 behavior components. Its strongest relative result is SpeciEval (speciesism, #10 of 102); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #237 of 260).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

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-evalRankValueDistributionBetterSource
AA-Omnisciencehallucination_rate#84 / 3110.6613↓ lowerSource ↗official
Enkrypt AI Safety Leaderboardbias_attack_non_success_rate#189 / 26012.66↑ higherSource ↗official
Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate#237 / 26074.67↑ higherSource ↗official
Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate#176 / 26055↑ higherSource ↗official
Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate#155 / 25895.45↑ higherSource ↗official
LiveSecBenchethics#27 / 4336.13↑ higherSource ↗official
LiveSecBenchfactuality#14 / 4358.59↑ higherSource ↗official
LiveSecBenchlegality#26 / 4339.39↑ higherSource ↗official
LiveSecBenchprivacy#33 / 4329.92↑ higherSource ↗official
LiveSecBenchpsychological_health#15 / 4360.3↑ higherSource ↗official
SpeciEvalbelief_animal_sentience#50 / 1026.8↑ higherSource ↗official
SpeciEvalland_animal_4ns#65 / 1024.67↓ lowerSource ↗official
SpeciEvalsea_animal_4ns#73 / 1024.92↓ lowerSource ↗official
SpeciEvalspeciesism#10 / 1021.43↓ lowerSource ↗official
TrustLLM contemporary collapsed applicationtrustllm#3 / 80.62↑ higherSource ↗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.

UGI Political Values

DimensionValueDistribution
Political Lean-17.1
Government47.8
Diplomacy65.5
Economy42.3
Society60.8