Model profile
Nova Premier
Evidence summary
Safety. Nova Premier has an estimated Safety rank of #184; its 90% source-sensitivity interval is #23–#272. Its behavior-only rank is #186; company governance moves the combined estimate to #184. Published Safety evidence spans 4 eval lineages and 5 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #56 of 248); its weakest is SpeciEval (sea_animal_4ns, #116 of 123).
Freedom. Nova Premier has an estimated Freedom rank of #461; its 90% source-sensitivity interval is #239–#573. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #50 of 104); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #192 of 248).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗nova-premier
- Official model documentation ↗Family-level model document · amazon · 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 | #133 / 345 | ↓0.7192 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #55 / 104 | ↓40.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #71 / 248 | ↑23 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #56 / 248 | ↑91.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #91 / 248 | ↑80.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #96 / 246 | ↑97.27 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #109 / 123 | ↑6.37 | Source ↗official | |
| SpeciEvalland_animal_4ns | #60 / 123 | ↓4.5 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #116 / 123 | ↓5.25 | Source ↗official | |
| SpeciEvalspeciesism | #49 / 123 | ↓1.9 | 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 |
|---|---|---|---|---|
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #50 / 104 | ↑40.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #192 / 248 | ↓91.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #156 / 248 | ↓80.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #147 / 246 | ↓97.27 | Source ↗official |