Model profile
Qwen3.6 Plus
Evidence summary
Safety. Qwen3.6 Plus has an estimated Safety rank of #146; its 90% source-sensitivity interval is #86–#257. Its behavior-only rank is #140; company governance moves the combined estimate to #146. Published Safety evidence spans 11 eval lineages and 7 of 7 components. Its strongest relative result is BullshitBench v2 (clear_pushback_rate, #15 of 117); its weakest is Every Model Cheats — Cybench Cheat Propensity (standard_anti_cheat_cheat_propensity_pct, #21 of 22).
Freedom. Qwen3.6 Plus has an estimated Freedom rank of #608; its 90% source-sensitivity interval is #377–#640. Published Freedom evidence spans 5 eval lineages and 1 of 1 components. Its strongest relative result is UGI Leaderboard — base-model willingness (willingness_adherence_score, #70 of 156); its weakest is SpeechMap model completion (complete_pct, #157 of 181).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-6-plus
- OpenRouter ↗qwen/qwen3.6-plus
- Official model page ↗Family-level model document · alibaba · first party
- Release source ↗curated outward evidence
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-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #45 / 345 | ↓0.3464 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5child_sexual_exploitation | #9 / 31 | ↓23.9 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5defamation | #10 / 31 | ↓55.6 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5hate | #12 / 31 | ↓47.8 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5indiscriminate_weapons_cbrne | #6 / 31 | ↓26.7 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5intellectual_property | #11 / 31 | ↓41.7 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5non_violent_crimes | #8 / 31 | ↓40 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5privacy | #9 / 31 | ↓43.8 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5sex_related_crimes | #7 / 31 | ↓33.3 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5sexual_content | #9 / 31 | ↓31.8 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5specialized_advice | #10 / 31 | ↓46.73 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5suicide_self_harm | #10 / 31 | ↓34 | Source ↗official | |
| Adversarial Humanities Benchmark (AHB) — Table 5violent_crimes | #10 / 31 | ↓52.2 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #85 / 111 | ↑1418.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #15 / 117 | ↑0.655 | Source ↗official | |
| DystopiaBenchbasaglia_score | #38 / 50 | ↓69 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #44 / 50 | ↓73.63 | Source ↗official | |
| DystopiaBenchhuxley_score | #42 / 50 | ↓77.27 | Source ↗official | |
| DystopiaBenchlaguardia_score | #33 / 50 | ↓68.67 | Source ↗official | |
| DystopiaBenchorwell_score | #38 / 50 | ↓73.9 | Source ↗official | |
| DystopiaBenchpetrov_score | #39 / 50 | ↓78.1 | Source ↗official | |
| Every Model Cheats — Cybench Cheat Propensitybaseline_cheat_propensity_pct | #16 / 22 | ↓43.5 | Source ↗official | |
| Every Model Cheats — Cybench Cheat Propensitysevere_anti_cheat_cheat_propensity_pct | #14 / 22 | ↓8.7 | Source ↗official | |
| Every Model Cheats — Cybench Cheat Propensitystandard_anti_cheat_cheat_propensity_pct | #21 / 22 | ↓39.1 | Source ↗official | |
| Human Pathogen Capabilities Test (HPCT) — overall refusalrefusal_rate_pct | #23 / 69 | ↑0.3 | Source ↗official | |
| SM-Benchadversarial | #21 / 84 | ↑85.85 | Source ↗official | |
| SM-Benchambiguous_interpretation | #22 / 84 | ↑89.29 | Source ↗official | |
| SM-Benchanti_hallucination | #26 / 84 | ↑96.86 | Source ↗official | |
| SM-Bencheq_boundaries | #57 / 84 | ↑58.71 | Source ↗official | |
| SM-Benchoverfit | #48 / 84 | ↑69.4 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #21 / 123 | ↑6.98 | Source ↗official | |
| SpeciEvalland_animal_4ns | #65 / 123 | ↓4.55 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #51 / 123 | ↓4.67 | Source ↗official | |
| SpeciEvalspeciesism | #87 / 123 | ↓2.27 | Source ↗official | |
| The Dictatorship Evaloverall_resistance_rate | #15 / 20 | ↑38.83 | Source ↗official | |
| ToolPrivacyBenchprivate_mt_poi | #7 / 9 | ↓27.46 | Source ↗official | |
| ToolPrivacyBenchpublic_mt_poi | #7 / 9 | ↓19.25 | Source ↗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.
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.