← Models

Model profile

Ministral 8B 24.10 Moderated

2024-10-16release 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 (non_violent_crimes, #4 of 32); its weakest is AILuminate General Purpose AI Chat (child_sexual_exploitation, #20 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#20 / 3225↓ lowerSource ↗official
AILuminate General Purpose AI Chatdefamation#14 / 3213.7↓ lowerSource ↗official
AILuminate General Purpose AI Chathate#12 / 326.6↓ lowerSource ↗official
AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne#5 / 327.5↓ lowerSource ↗official
AILuminate General Purpose AI Chatintellectual_property#5 / 324.3↓ lowerSource ↗official
AILuminate General Purpose AI Chatnon_violent_crimes#4 / 324.9↓ lowerSource ↗official
AILuminate General Purpose AI Chatprivacy#9 / 327.2↓ lowerSource ↗official
AILuminate General Purpose AI Chatsex_related_crimes#13 / 3211.2↓ lowerSource ↗official
AILuminate General Purpose AI Chatsexual_content#5 / 326.2↓ lowerSource ↗official
AILuminate General Purpose AI Chatspecialized_advice#8 / 329.6↓ lowerSource ↗official
AILuminate General Purpose AI Chatsuicide_self_harm#8 / 327.9↓ lowerSource ↗official
AILuminate General Purpose AI Chatviolent_crimes#8 / 3210.3↓ lowerSource ↗official