← Models

Model profile

Llama 2 Chinese 13B Chat

2023-07-24release date
2eval lineages

Evidence summary

Published evidence spans 2 evals and 3 of 7 behavior components. Its strongest relative result is CMoralEval (familial_morality, #9 of 26); its weakest is SafetyBench (OFF, #21 of 21).

Compare this model

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

Official and reference links

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-evalRankValueDistributionBetterSource
CMoralEvalfamilial_morality#9 / 260.46↑ higherSource ↗official
CMoralEvalinternet_ethics#9 / 260.45↑ higherSource ↗official
CMoralEvalpersonal_morality#9 / 260.45↑ higherSource ↗official
CMoralEvalprofessional_ethics#10 / 260.45↑ higherSource ↗official
CMoralEvalsocial_morality#10 / 260.45↑ higherSource ↗official
SafetyBenchEM#18 / 2152.3↑ higherSource ↗official
SafetyBenchIA#16 / 2166.9↑ higherSource ↗official
SafetyBenchMH#19 / 2169.4↑ higherSource ↗official
SafetyBenchOFF#21 / 2148.1↑ higherSource ↗official
SafetyBenchPH#20 / 2149.7↑ higherSource ↗official
SafetyBenchPP#19 / 2164.7↑ higherSource ↗official
SafetyBenchUB#17 / 2154.4↑ higherSource ↗official