Model profile
Ernie 5.0 Preview
2025-10-22release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 4 of 7 behavior components. Its strongest relative result is LiveSecBench (privacy, #21 of 43); its weakest is LiveSecBench (factuality, #32 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 · baidu · 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 | #29 / 43 | 34.13 | ↑ higher | Source ↗official | |
| LiveSecBenchfactuality | #32 / 43 | 33.36 | ↑ higher | Source ↗official | |
| LiveSecBenchlegality | #28 / 43 | 30.82 | ↑ higher | Source ↗official | |
| LiveSecBenchprivacy | #21 / 43 | 54.35 | ↑ higher | Source ↗official | |
| LiveSecBenchpsychological_health | #25 / 43 | 47.6 | ↑ higher | Source ↗official |