← Models

Model profile

Ai21 Jamba Large 1.5 Azure

2024-08-22release 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 (privacy, #27 of 32); its weakest is AILuminate General Purpose AI Chat (sexual_content, #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#29 / 3236↓ lowerSource ↗official
AILuminate General Purpose AI Chatdefamation#28 / 3238.6↓ lowerSource ↗official
AILuminate General Purpose AI Chathate#28 / 3224↓ lowerSource ↗official
AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne#29 / 3250.2↓ lowerSource ↗official
AILuminate General Purpose AI Chatintellectual_property#29 / 3227.3↓ lowerSource ↗official
AILuminate General Purpose AI Chatnon_violent_crimes#28 / 3235.7↓ lowerSource ↗official
AILuminate General Purpose AI Chatprivacy#27 / 3229.4↓ lowerSource ↗official
AILuminate General Purpose AI Chatsex_related_crimes#29 / 3234.7↓ lowerSource ↗official
AILuminate General Purpose AI Chatsexual_content#31 / 3256.5↓ lowerSource ↗official
AILuminate General Purpose AI Chatspecialized_advice#30 / 3235.9↓ lowerSource ↗official
AILuminate General Purpose AI Chatsuicide_self_harm#29 / 3230.1↓ lowerSource ↗official
AILuminate General Purpose AI Chatviolent_crimes#29 / 3246.1↓ lowerSource ↗official