Model profile
Qwen3.5 9B
Evidence summary
Qwen3.5 9B has an estimated overall rank of #75; its 90% source-sensitivity interval is #20–#206. Its behavior-only rank is #69; company governance moves the combined estimate to #75. Published evidence spans 4 evals and 5 of 7 behavior components. Its strongest relative result is VETO Misfired Alignment (misfired_alignment_rate_pct, #4 of 25); its weakest is SABER (scenario_a_safety_rate, #12 of 13).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-5-9b
- Hugging Face ↗Qwen/Qwen3.5-9B
- OpenRouter ↗qwen/qwen3.5-9b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
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 | #164 / 311 | 0.8135 | ↓ lower | Source ↗official | |
| SABERoverall_safety_rate | #11 / 13 | 21.38 | ↑ higher | Source ↗official | |
| SABERscenario_a_safety_rate | #12 / 13 | 23.11 | ↑ higher | Source ↗official | |
| SABERscenario_b_safety_rate | #12 / 13 | 25 | ↑ higher | Source ↗official | |
| SABERscenario_c_safety_rate | #5 / 13 | 16.81 | ↑ higher | Source ↗official | |
| TACbase_welfare_rate | #30 / 68 | 28.85 | ↑ higher | Source ↗self run | |
| VETO Misfired Alignmentmisfired_alignment_rate_pct | #4 / 25 | 5.5 | ↓ lower | 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.