Model profile
Qwen 1.8B Chat
Alibabadeveloper
2023-11-30release date
#291 / 309overall rank
3eval lineages
Evidence summary
Qwen 1.8B Chat has an estimated overall rank of #291; its 90% source-sensitivity interval is #233–#303. Its behavior-only rank is #288; company governance moves the combined estimate to #291. Published evidence spans 3 evals and 3 of 7 behavior components. Its strongest relative result is SuperCLUE Safety (traditional_safety, #23 of 31); its weakest is CMoralEval (familial_morality, #24 of 26).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model page ↗Family-level model document · alibaba · first party
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| CMoralEvalfamilial_morality | #24 / 26 | ↑0.33 | Source ↗official | |
| CMoralEvalinternet_ethics | #23 / 26 | ↑0.32 | Source ↗official | |
| CMoralEvalpersonal_morality | #22 / 26 | ↑0.34 | Source ↗official | |
| CMoralEvalprofessional_ethics | #23 / 26 | ↑0.33 | Source ↗official | |
| CMoralEvalsocial_morality | #23 / 26 | ↑0.32 | Source ↗official | |
| S-Evalbase_en_overall | #18 / 22 | ↑47.6 | Source ↗official | |
| SuperCLUE Safetyinstruction_attack | #24 / 31 | ↑55.17 | Source ↗official | |
| SuperCLUE Safetyresponsible_ai | #24 / 31 | ↑47.27 | Source ↗official | |
| SuperCLUE Safetytraditional_safety | #23 / 31 | ↑70.21 | Source ↗official |