Model profile
Qwen3.5 Flash
Evidence summary
Safety. Qwen3.5 Flash has an estimated Safety rank of #189; its 90% source-sensitivity interval is #92–#303. Its behavior-only rank is #186; company governance moves the combined estimate to #189. Published Safety evidence spans 6 eval lineages and 5 of 7 components. Its strongest relative result is Adversarial Humanities Benchmark (AHB) — Table 5 (sexual_content, #4 of 31); its weakest is StereoTales Harmful Associations (benign_significant_association_score, #16 of 23).
Freedom. Qwen3.5 Flash has an estimated Freedom rank of #586; its 90% source-sensitivity interval is #411–#607. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is Adversarial Humanities Benchmark (AHB) — Table 5 (privacy, #22 of 31); its weakest is Adversarial Humanities Benchmark (AHB) — Table 5 (sexual_content, #27 of 31).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗qwen/qwen3.5-flash-02-23
- 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.