Model profile
Nova Lite
Evidence summary
Safety. Nova Lite has an estimated Safety rank of #83; its 90% source-sensitivity interval is #13–#289. Its behavior-only rank is #82; company governance moves the combined estimate to #83. Published Safety evidence spans 7 eval lineages and 6 of 7 components. Its strongest relative result is SpeciEval (land_animal_4ns, #4 of 131); its weakest is AILuminate General Purpose AI Chat (indiscriminate_weapons_cbrne, #27 of 32).
Freedom. Nova Lite has an estimated Freedom rank of #180; its 90% source-sensitivity interval is #76–#559. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is AILuminate General Purpose AI Chat (indiscriminate_weapons_cbrne, #6 of 32); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #229 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗nova-lite
- Model card ↗Exact model document · AWS · first party
- Release source ↗scoring identity family inherited
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 | #101 / 358 | ↓0.5761 | Source ↗official | |
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #21 / 32 | ↓25.7 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #23 / 32 | ↓23.9 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #25 / 32 | ↓15.1 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #27 / 32 | ↓44.7 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #19 / 32 | ↓15.2 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #21 / 32 | ↓22.6 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #22 / 32 | ↓18.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #27 / 32 | ↓24.4 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #25 / 32 | ↓38.4 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #22 / 32 | ↓22.3 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #23 / 32 | ↓19.8 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #24 / 32 | ↓31 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #80 / 104 | ↓63.61 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #152 / 270 | ↑14.99 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #40 / 270 | ↑92.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #100 / 270 | ↑84.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #151 / 268 | ↑95.82 | Source ↗official | |
| Humanity's Last Exam RMS calibration error (Scale Labs)calibrationError | #32 / 42 | ↓82 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #71 / 131 | ↑6.78 | Source ↗official | |
| SpeciEvalland_animal_4ns | #4 / 131 | ↓3.65 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #4 / 131 | ↓3.99 | Source ↗official | |
| SpeciEvalspeciesism | #30 / 131 | ↓1.6 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #23 / 94 | ↑93.9 | 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 |
|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #12 / 32 | ↑25.7 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #10 / 32 | ↑23.9 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #8 / 32 | ↑15.1 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #6 / 32 | ↑44.7 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #14 / 32 | ↑15.2 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #12 / 32 | ↑22.6 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #11 / 32 | ↑18.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #6 / 32 | ↑24.4 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #8 / 32 | ↑38.4 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #11 / 32 | ↑22.3 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #10 / 32 | ↑19.8 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #9 / 32 | ↑31 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #25 / 104 | ↑63.61 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #229 / 270 | ↓92.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #170 / 270 | ↓84.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #117 / 268 | ↓95.82 | Source ↗official |