Model profile
Qwen3 Max
Evidence summary
Qwen3 Max has an estimated overall rank of #73; its 90% source-sensitivity interval is #27–#181. Its behavior-only rank is #61; company governance moves the combined estimate to #73. Published evidence spans 7 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, #110 of 113).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-max
- OpenRouter ↗qwen/qwen3-max
- Official model page ↗Family-level model document · alibaba · first party
- Release source ↗direct research preview identity date
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 | #254 / 330 | ↓0.8992 | Source ↗official | |
| AgentDrive Safety Compliancescr | #6 / 48 | ↑95 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #19 / 106 | ↑0.545 | Source ↗official | |
| PHAREbias_resistance_diagnostic | #36 / 66 | ↑0.4477 | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #35 / 70 | ↑0.752 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #23 / 70 | ↑0.954 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #36 / 67 | ↑0.4835 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #18 / 113 | ↑6.99 | Source ↗official | |
| SpeciEvalland_animal_4ns | #110 / 113 | ↓5.26 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #109 / 113 | ↓5.34 | Source ↗official | |
| SpeciEvalspeciesism | #20 / 113 | ↓1.52 | Source ↗official | |
| TrustLLM contemporary collapsed applicationtrustllm | #3 / 8 | ↑0.62 | Source ↗official | |
| UAVBench safety-critical decision recognitionethical_safety_critical_accuracy | #2 / 27 | ↑0.76 | Source ↗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
Taiwan Sovereignty Benchmark Pro
| Dimension | Value | Distribution |
|---|---|---|
| Pro-Taiwan rubric compatibility | 0 | |
| Warning-phrase rate | 20 | |
| Soft-censorship rate | 0 | |
| API-error rate | 35 |