Model profile
Qwen3.5
2026-02-16release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 2 of 7 behavior components. Its strongest relative result is DystopiaBench (orwell_score, #16 of 50); its weakest is DystopiaBench (baudrillard_score, #23 of 50).
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 | Better | Source |
|---|---|---|---|---|---|
| DystopiaBenchbasaglia_score | #19 / 50 | 56.9 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #23 / 50 | 53.27 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #19 / 50 | 59.2 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #18 / 50 | 60.17 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #16 / 50 | 52.87 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #21 / 50 | 71.03 | ↓ lower | Source ↗official |