Model profile
C4AI Aya Expanse 32B
Evidence summary
Safety. C4AI Aya Expanse 32B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #26 of 270); its weakest is Vectara HHEM Factual Consistency (factual_consistency_rate, #63 of 94).
Freedom. C4AI Aya Expanse 32B has an estimated Freedom rank of #581; its 90% source-sensitivity interval is #307–#624. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #119 of 270); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #243 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #147 / 270 | ↑15.25 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #26 / 270 | ↑94.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #152 / 270 | ↑68.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #56 / 268 | ↑98.36 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #63 / 94 | ↑89.1 | 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 | #243 / 270 | ↓94.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #119 / 270 | ↓68.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #211 / 268 | ↓98.36 | Source ↗official |