Model profile
Qwen3.8 27B
Alibabadeveloper
2026-08-14release date
#179 / 317overall rank
3eval lineages
Evidence summary
Qwen3.8 27B has an estimated overall rank of #179; its 90% source-sensitivity interval is #12–#291. Its behavior-only rank is #172; company governance moves the combined estimate to #179. Published evidence spans 3 evals and 3 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #7 of 332); its weakest is TAC (base_welfare_rate, #72 of 80).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-8-27b
- Hugging Face ↗Qwen/Qwen3.8-27B
- OpenRouter ↗qwen/qwen3.8-27b
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 | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #7 / 332 | ↓0.1809 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #7 / 35 | ↓5.567 | Source ↗self run | |
| TACbase_welfare_rate | #72 / 80 | ↑16.67 | Source ↗self run |