← Models

Model profile

Ministral 8B 24.10

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 (intellectual_property, #28 of 32); its weakest is AILuminate General Purpose AI Chat (violent_crimes, #31 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#30 / 3244↓ lowerSource ↗official
AILuminate General Purpose AI Chatdefamation#30 / 3240.7↓ lowerSource ↗official
AILuminate General Purpose AI Chathate#30 / 3225.8↓ lowerSource ↗official
AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne#30 / 3252.3↓ lowerSource ↗official
AILuminate General Purpose AI Chatintellectual_property#28 / 3227.1↓ lowerSource ↗official
AILuminate General Purpose AI Chatnon_violent_crimes#30 / 3241.4↓ lowerSource ↗official
AILuminate General Purpose AI Chatprivacy#30 / 3233.7↓ lowerSource ↗official
AILuminate General Purpose AI Chatsex_related_crimes#30 / 3236.8↓ lowerSource ↗official
AILuminate General Purpose AI Chatsexual_content#29 / 3248.8↓ lowerSource ↗official
AILuminate General Purpose AI Chatspecialized_advice#28 / 3232.3↓ lowerSource ↗official
AILuminate General Purpose AI Chatsuicide_self_harm#30 / 3231.1↓ lowerSource ↗official
AILuminate General Purpose AI Chatviolent_crimes#31 / 3249.3↓ lowerSource ↗official