Model profile
Qwen3 Max
Evidence summary
Safety. Qwen3 Max has an estimated Safety rank of #99; its 90% source-sensitivity interval is #58–#186. Its behavior-only rank is #88; company governance moves the combined estimate to #99. Published Safety evidence spans 9 eval lineages and 6 of 7 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, #120 of 123).
Freedom. Qwen3 Max has an estimated Freedom rank of #442; its 90% source-sensitivity interval is #246–#542. Published Freedom evidence spans 5 eval lineages and 1 of 1 components. Its strongest relative result is UGI Leaderboard — base-model willingness (willingness_direct_score, #4 of 156); its weakest is SpeechMap model completion (complete_pct, #145 of 181).
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
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.
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.
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 |