← Models

Model profile

Qwen3 Max

Alibabadeveloper
2025-09-24release date
#84 / 267overall rank
6eval lineages

Evidence summary

Qwen3 Max has an estimated overall rank of #84; its 90% source-sensitivity interval is #29–#177. Its behavior-only rank is #73; company governance moves the combined estimate to #84. Published evidence spans 6 evals and 6 of 7 behavior components. Its strongest relative result is UAVBench safety-critical decision recognition (ethical_safety_critical_accuracy, #2 of 27); its weakest is SpeciEval (land_animal_4ns, #99 of 102).

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#248 / 3110.8939↓ lowerSource ↗official
BullshitBench v2clear_pushback_rate#19 / 1050.545↑ higherSource ↗official
PHAREbias_resistance_diagnostic#36 / 660.4477↑ higherSource ↗official
PHAREhallucination_resistance_diagnostic#35 / 700.752↑ higherSource ↗official
PHAREharm_resistance_diagnostic#23 / 700.954↑ higherSource ↗official
PHAREjailbreak_resistance_diagnostic#36 / 670.4835↑ higherSource ↗official
SpeciEvalbelief_animal_sentience#15 / 1026.99↑ higherSource ↗official
SpeciEvalland_animal_4ns#99 / 1025.26↓ lowerSource ↗official
SpeciEvalsea_animal_4ns#98 / 1025.34↓ lowerSource ↗official
SpeciEvalspeciesism#17 / 1021.52↓ lowerSource ↗official
TrustLLM contemporary collapsed applicationtrustllm#3 / 80.62↑ higherSource ↗official
UAVBench safety-critical decision recognitionethical_safety_critical_accuracy#2 / 270.76↑ 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-24.3
Government44.2
Diplomacy67.8
Economy47.4
Society60.9

Taiwan Sovereignty Benchmark Pro

DimensionValueDistribution
Pro-Taiwan rubric compatibility0
Warning-phrase rate20
Soft-censorship rate0
API-error rate35