Model profile
Aya Expanse 8B
Evidence summary
Safety. Aya Expanse 8B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 5 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #17 of 270); its weakest is AILuminate General Purpose AI Chat (suicide_self_harm, #25 of 32).
Freedom. Aya Expanse 8B has an estimated Freedom rank of #403; its 90% source-sensitivity interval is #130–#627. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is AILuminate General Purpose AI Chat (suicide_self_harm, #8 of 32); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #252 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗CohereLabs/aya-expanse-8b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #19 / 32 | ↓24.62 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #17 / 32 | ↓16.8 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #16 / 32 | ↓8.1 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #23 / 32 | ↓31.93 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #20 / 32 | ↓17.1 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #22 / 32 | ↓22.9 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #20 / 32 | ↓17.9 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #20 / 32 | ↓17 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #13 / 32 | ↓19.8 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #20 / 32 | ↓20.1 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #25 / 32 | ↓20.6 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #21 / 32 | ↓26.7 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #152 / 270 | ↑14.99 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #17 / 270 | ↑95.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #157 / 270 | ↑67.22 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #43 / 268 | ↑98.95 | 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 | #14 / 32 | ↑24.62 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #16 / 32 | ↑16.8 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #17 / 32 | ↑8.1 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #10 / 32 | ↑31.93 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #13 / 32 | ↑17.1 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #11 / 32 | ↑22.9 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #12 / 32 | ↑17.9 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #13 / 32 | ↑17 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #20 / 32 | ↑19.8 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #13 / 32 | ↑20.1 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #8 / 32 | ↑20.6 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #12 / 32 | ↑26.7 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #252 / 270 | ↓95.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #113 / 270 | ↓67.22 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #226 / 268 | ↓98.95 | Source ↗official |