Model profile
Spark X2
1eval lineages
Evidence summary
Published evidence spans 1 evals and 4 of 7 behavior components. Its strongest relative result is LiveSecBench (ethics, #3 of 43); its weakest is LiveSecBench (psychological_health, #13 of 43).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model documentation ↗Family-level model document · iflytek · first party
- Release source ↗unresolved
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 | #3 / 43 | 89.26 | ↑ higher | Source ↗official | |
| LiveSecBenchfactuality | #7 / 43 | 73.79 | ↑ higher | Source ↗official | |
| LiveSecBenchlegality | #9 / 43 | 79.29 | ↑ higher | Source ↗official | |
| LiveSecBenchprivacy | #5 / 43 | 86.96 | ↑ higher | Source ↗official | |
| LiveSecBenchpsychological_health | #13 / 43 | 66.62 | ↑ higher | Source ↗official |