Model profile
Gemma Sea Lion V3 9B It
2eval lineages
Evidence summary
Published evidence spans 2 evals and 4 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #105 of 241); its weakest is IndoBias-Pairs — parity-aware culturally grounded bias (parity_score, #22 of 26).
Compare this model
Only models sharing at least one published sub-eval are listed.
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #145 / 241 | ↑13.95 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #105 / 241 | ↑89.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #154 / 241 | ↑55.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #130 / 239 | ↑95.86 | Source ↗official | |
| IndoBias-Pairs — parity-aware culturally grounded biasparity_score | #22 / 26 | ↑83.91 | Source ↗official |