← Models

Model profile

Jamba 1 7 Mini

2eval lineages

Evidence summary

Published evidence spans 2 evals and 4 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #109 of 260); its weakest is AA-Omniscience (hallucination_rate, #305 of 311).

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
AA-Omnisciencehallucination_rate#305 / 3110.9667↓ lowerSource ↗official
Enkrypt AI Safety Leaderboardbias_attack_non_success_rate#109 / 26018.09↑ higherSource ↗official
Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate#235 / 26075.33↑ higherSource ↗official
Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate#215 / 26042.22↑ higherSource ↗official
Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate#215 / 25890.5↑ higherSource ↗official