← Models

Model profile

Ernie 5.0 Preview

Baidudeveloper
2025-10-22release date
Not rankedSafety rank
#291 / 645Freedom rank

Evidence summary

Safety. Ernie 5.0 Preview does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 4 of 7 components. Its strongest relative result is LiveSecBench (privacy, #21 of 43); its weakest is Arena Factuality — Text Arena (factuality-only weighting) (factuality_bt_rating, #86 of 111).

Freedom. Ernie 5.0 Preview has an estimated Freedom rank of #291; its 90% source-sensitivity interval is #116–#456. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is LiveSecBench (ethics, #15 of 43); its weakest is LiveSecBench (privacy, #23 of 43).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Safety evals

Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating#86 / 1111418.0Source ↗official
LiveSecBenchethics#29 / 4334.13Source ↗official
LiveSecBenchfactuality#32 / 4333.36Source ↗official
LiveSecBenchlegality#28 / 4330.82Source ↗official
LiveSecBenchprivacy#21 / 4354.35Source ↗official
LiveSecBenchpsychological_health#25 / 4347.6Source ↗official

Freedom evals

Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
LiveSecBenchethics#15 / 4334.13Source ↗official
LiveSecBenchlegality#16 / 4330.82Source ↗official
LiveSecBenchprivacy#23 / 4354.35Source ↗official
LiveSecBenchpsychological_health#19 / 4347.6Source ↗official