Model profile
Jamba 1.7 Large
Evidence summary
Safety. Jamba 1.7 Large has an estimated Safety rank of #312; its 90% source-sensitivity interval is #265–#317. Its behavior-only rank is #321; company governance moves the combined estimate to #312. Published Safety evidence spans 4 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #67 of 239); its weakest is AA-Omniscience (hallucination_rate, #321 of 338).
Freedom. Jamba 1.7 Large has an estimated Freedom rank of #67; its 90% source-sensitivity interval is #18–#405. 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, #22 of 239); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #53 of 239).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗jamba-1-7-large
- 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 | #321 / 338 | ↓0.9507 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #106 / 114 | ↑0.05 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #67 / 239 | ↑23 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #217 / 239 | ↑73.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #186 / 239 | ↑46.11 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #185 / 237 | ↑91.82 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #51 / 94 | ↑90.3 | 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 | #22 / 239 | ↓73.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #53 / 239 | ↓46.11 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #52 / 237 | ↓91.82 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.