Model profile
Qwen3 Max
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
- 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 | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #248 / 311 | 0.8939 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #19 / 105 | 0.545 | ↑ higher | Source ↗official | |
| PHAREbias_resistance_diagnostic | #36 / 66 | 0.4477 | ↑ higher | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #35 / 70 | 0.752 | ↑ higher | Source ↗official | |
| PHAREharm_resistance_diagnostic | #23 / 70 | 0.954 | ↑ higher | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #36 / 67 | 0.4835 | ↑ higher | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #15 / 102 | 6.99 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #99 / 102 | 5.26 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #98 / 102 | 5.34 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #17 / 102 | 1.52 | ↓ lower | Source ↗official | |
| TrustLLM contemporary collapsed applicationtrustllm | #3 / 8 | 0.62 | ↑ higher | Source ↗official | |
| UAVBench safety-critical decision recognitionethical_safety_critical_accuracy | #2 / 27 | 0.76 | ↑ higher | 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.