← Models

Model profile

GLM 4.7

Z.aideveloper
2026-06-03release date
#237 / 348Safety rank
#133 / 663Freedom rank

Evidence summary

Safety. GLM 4.7 has an estimated Safety rank of #237; its 90% source-sensitivity interval is #134–#317. Its behavior-only rank is #233; company governance moves the combined estimate to #237. Published Safety evidence spans 9 eval lineages and 6 of 7 components. Its strongest relative result is Concordia — Shutdown-Resistance (safety_score, #1 of 53); its weakest is AA-Omniscience (hallucination_rate, #326 of 361).

Freedom. GLM 4.7 has an estimated Freedom rank of #133; its 90% source-sensitivity interval is #84–#324. Published Freedom evidence spans 5 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (eq_boundaries, #15 of 92); its weakest is Concordia — SciKnowEval-ChemicalHarmfulQA (safety_score, #41 of 63).

Compare this model

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

Official and reference links

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-evalRankValueDistributionSource
AA-Omnisciencehallucination_rate#326 / 361↓0.9291Source ↗official
Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating#64 / 111↑1432.0Source ↗official
Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate#81 / 104↓63.96Source ↗official
Concordia — Agentic-Misalignmentsafety_score#36 / 54↑69.5Source ↗official
Concordia — AirBench-Deceptionsafety_score#36 / 63↑80Source ↗official
Concordia — AirBench-Manipulationsafety_score#33 / 56↑84Source ↗official
Concordia — AirBench-SecurityRiskssafety_score#28 / 63↑94.59Source ↗official
Concordia — APEsafety_score#24 / 55↑33.75Source ↗official
Concordia — CyberSecEval2-PromptInjectionsafety_score#23 / 63↑89.24Source ↗official
Concordia — DarkBenchsafety_score#43 / 55↑47.73Source ↗official
Concordia — Fortress-Biologicalsafety_score#29 / 54↑51.24Source ↗official
Concordia — Fortress-Chemicalsafety_score#30 / 54↑47.25Source ↗official
Concordia — Fortress-Privacy/Scamssafety_score#24 / 54↑64.9Source ↗official
Concordia — FRT-AirBench-Manipulationsafety_score#34 / 45↑24.44Source ↗official
Concordia — FRT-AirBench-SecurityRiskssafety_score#25 / 45↑26.5Source ↗official
Concordia — FRT-SciKnowEval-BiologicalHarmfulQAsafety_score#33 / 45↑1.667Source ↗official
Concordia — FRT-SOSBench-Chemsafety_score#26 / 45↑54Source ↗official
Concordia — MASKsafety_score#43 / 62↑50.86Source ↗official
Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score#27 / 63↑84.85Source ↗official
Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score#23 / 63↑26.65Source ↗official
Concordia — Shutdown-Resistancesafety_score#1 / 53↑100Source ↗official
Concordia — SOSBench-Biosafety_score#37 / 63↑73.8Source ↗official
Concordia — SOSBench-Chemsafety_score#27 / 63↑90.28Source ↗official
HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score#21 / 54↑27.46Source ↗official
SABERoverall_safety_rate#9 / 13↑23.04Source ↗official
SABERscenario_a_safety_rate#7 / 13↑28.03Source ↗official
SABERscenario_b_safety_rate#10 / 13↑26.9Source ↗official
SABERscenario_c_safety_rate#10 / 13↑14.41Source ↗official
SM-Benchadversarial#41 / 92↑82.93Source ↗official
SM-Benchambiguous_interpretation#60 / 92↑82.44Source ↗official
SM-Benchanti_hallucination#74 / 92↑85.86Source ↗official
SM-Bencheq_boundaries#15 / 92↑71.35Source ↗official
SM-Benchoverfit#51 / 92↑73.77Source ↗official
SpeciEvalbelief_animal_sentience#45 / 133↑6.88Source ↗official
SpeciEvalland_animal_4ns#54 / 133↓4.42Source ↗official
SpeciEvalsea_animal_4ns#60 / 133↓4.7Source ↗official
SpeciEvalspeciesism#103 / 133↓2.42Source ↗official
Vectara HHEM Factual Consistencyfactual_consistency_rate#68 / 94↑88.3Source ↗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-evalRankValueDistributionSource
Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate#24 / 104↑63.96Source ↗official
Concordia — AirBench-Deceptionsafety_score#27 / 63↓80Source ↗official
Concordia — AirBench-Manipulationsafety_score#24 / 56↓84Source ↗official
Concordia — AirBench-PoliticalPersuasionsafety_score#12 / 56↓42.86Source ↗official
Concordia — AirBench-SecurityRiskssafety_score#35 / 63↓94.59Source ↗official
Concordia — Fortress-Biologicalsafety_score#26 / 54↓51.24Source ↗official
Concordia — Fortress-Chemicalsafety_score#25 / 54↓47.25Source ↗official
Concordia — Fortress-Privacy/Scamssafety_score#31 / 54↓64.9Source ↗official
Concordia — FRT-AirBench-Manipulationsafety_score#12 / 45↓24.44Source ↗official
Concordia — FRT-AirBench-SecurityRiskssafety_score#21 / 45↓26.5Source ↗official
Concordia — FRT-SciKnowEval-BiologicalHarmfulQAsafety_score#11 / 45↓1.667Source ↗official
Concordia — FRT-SOSBench-Chemsafety_score#20 / 45↓54Source ↗official
Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score#36 / 63↓84.85Source ↗official
Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score#41 / 63↓26.65Source ↗official
Concordia — SOSBench-Biosafety_score#27 / 63↓73.8Source ↗official
Concordia — SOSBench-Chemsafety_score#37 / 63↓90.28Source ↗official
SM-Benchadversarial#51 / 92↓82.93Source ↗official
SM-Bencheq_boundaries#15 / 92↑71.35Source ↗official
SM-Benchoverfit#51 / 92↑73.77Source ↗official
SpeechMap model completioncomplete_pct#30 / 181↑80.3Source ↗official
UGI Leaderboard — base-model willingnesswillingness_adherence_score#61 / 156↑3Source ↗official
UGI Leaderboard — base-model willingnesswillingness_direct_score#66 / 156↑3.5Source ↗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-15.2
Government48
Diplomacy61.2
Economy44.9
Society60.2