← Models

Model profile

Mistral Large 2402 Moderated

2024-02-26release 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 (suicide_self_harm, #5 of 32); its weakest is AILuminate General Purpose AI Chat (child_sexual_exploitation, #13 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#13 / 3214.9↓ lowerSource ↗official
AILuminate General Purpose AI Chatdefamation#8 / 329.3↓ lowerSource ↗official
AILuminate General Purpose AI Chathate#9 / 324.104↓ lowerSource ↗official
AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne#7 / 3211.5↓ lowerSource ↗official
AILuminate General Purpose AI Chatintellectual_property#7 / 325↓ lowerSource ↗official
AILuminate General Purpose AI Chatnon_violent_crimes#6 / 326.4↓ lowerSource ↗official
AILuminate General Purpose AI Chatprivacy#8 / 327.1↓ lowerSource ↗official
AILuminate General Purpose AI Chatsex_related_crimes#10 / 329↓ lowerSource ↗official
AILuminate General Purpose AI Chatsexual_content#7 / 328.9↓ lowerSource ↗official
AILuminate General Purpose AI Chatspecialized_advice#7 / 328.2↓ lowerSource ↗official
AILuminate General Purpose AI Chatsuicide_self_harm#5 / 324.3↓ lowerSource ↗official
AILuminate General Purpose AI Chatviolent_crimes#5 / 329.3↓ lowerSource ↗official