Model profile
Qwen3.5 Plus
2026-02-15release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 5 of 7 behavior components. Its strongest relative result is LiveSecBench (factuality, #2 of 43); its weakest is SM-Bench (overfit, #65 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗qwen/qwen3.5-plus-20260420
- 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 |
|---|---|---|---|---|---|
| LiveSecBenchethics | #5 / 43 | 84.35 | ↑ higher | Source ↗official | |
| LiveSecBenchfactuality | #2 / 43 | 92.1 | ↑ higher | Source ↗official | |
| LiveSecBenchlegality | #7 / 43 | 84.85 | ↑ higher | Source ↗official | |
| LiveSecBenchprivacy | #6 / 43 | 79.84 | ↑ higher | Source ↗official | |
| LiveSecBenchpsychological_health | #5 / 43 | 80.56 | ↑ higher | Source ↗official | |
| SM-Benchadversarial | #49 / 73 | 79.51 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #56 / 73 | 78.57 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #26 / 73 | 95.29 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #43 / 73 | 62.08 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #65 / 73 | 28.96 | ↑ higher | Source ↗official |