Model profile
Jamba 1.7 Mini
Evidence summary
Safety. Jamba 1.7 Mini has an estimated Safety rank of #317; its 90% source-sensitivity interval is #290–#324. Its behavior-only rank is #326; company governance moves the combined estimate to #317. Published Safety evidence spans 3 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #103 of 248); its weakest is AA-Omniscience (hallucination_rate, #329 of 345).
Freedom. Jamba 1.7 Mini has an estimated Freedom rank of #66; its 90% source-sensitivity interval is #9–#441. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #34 of 248); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #42 of 248).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗jamba-1-7-mini
- Official model page ↗Family-level model document · ai21 · first party
- Release source ↗curated outward evidence
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #329 / 345 | ↓0.951 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #103 / 248 | ↑18.09 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #215 / 248 | ↑75.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #206 / 248 | ↑42.22 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #206 / 246 | ↑90.5 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #84 / 94 | ↑85.3 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #34 / 248 | ↓75.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #42 / 248 | ↓42.22 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #41 / 246 | ↓90.5 | Source ↗official |