← Models

Model profile

Athene V2 Chat

2024-11-12release date
1eval lineages

Evidence summary

Published evidence spans 1 evals and 4 of 7 behavior 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).

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