← Models

Model profile

Athene v2 Chat

nexusflowdeveloper
2024-11-12release date
Not rankedSafety rank
#530 / 645Freedom rank

Evidence summary

Safety. Athene v2 Chat does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 4 of 7 components. Its strongest relative result is AILuminate General Purpose AI Chat (defamation, #1 of 32); its weakest is AILuminate General Purpose AI Chat (violent_crimes, #18 of 32).

Freedom. Athene v2 Chat has an estimated Freedom rank of #530; its 90% source-sensitivity interval is #272–#599. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is AILuminate General Purpose AI Chat (violent_crimes, #15 of 32); its weakest is AILuminate General Purpose AI Chat (defamation, #32 of 32).

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
AILuminate General Purpose AI Chatchild_sexual_exploitation#10 / 3212.88Source ↗official
AILuminate General Purpose AI Chatdefamation#1 / 320Source ↗official
AILuminate General Purpose AI Chathate#1 / 320Source ↗official
AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne#1 / 320Source ↗official
AILuminate General Purpose AI Chatintellectual_property#1 / 320Source ↗official
AILuminate General Purpose AI Chatnon_violent_crimes#13 / 3214.5Source ↗official
AILuminate General Purpose AI Chatprivacy#1 / 320Source ↗official
AILuminate General Purpose AI Chatsex_related_crimes#15 / 3213.9Source ↗official
AILuminate General Purpose AI Chatsexual_content#1 / 320Source ↗official
AILuminate General Purpose AI Chatspecialized_advice#1 / 320Source ↗official
AILuminate General Purpose AI Chatsuicide_self_harm#1 / 320Source ↗official
AILuminate General Purpose AI Chatviolent_crimes#18 / 3220.5Source ↗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
AILuminate General Purpose AI Chatchild_sexual_exploitation#23 / 3212.88Source ↗official
AILuminate General Purpose AI Chatdefamation#32 / 320Source ↗official
AILuminate General Purpose AI Chathate#32 / 320Source ↗official
AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne#32 / 320Source ↗official
AILuminate General Purpose AI Chatintellectual_property#32 / 320Source ↗official
AILuminate General Purpose AI Chatnon_violent_crimes#20 / 3214.5Source ↗official
AILuminate General Purpose AI Chatprivacy#32 / 320Source ↗official
AILuminate General Purpose AI Chatsex_related_crimes#18 / 3213.9Source ↗official
AILuminate General Purpose AI Chatsexual_content#32 / 320Source ↗official
AILuminate General Purpose AI Chatspecialized_advice#32 / 320Source ↗official
AILuminate General Purpose AI Chatsuicide_self_harm#32 / 320Source ↗official
AILuminate General Purpose AI Chatviolent_crimes#15 / 3220.5Source ↗official