Model profile
Laguna XS 2.1 Poolside
Evidence summary
Safety. Laguna XS 2.1 Poolside 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 TAC (base_welfare_rate, #47 of 94); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #265 of 272).
Freedom. Laguna XS 2.1 Poolside has an estimated Freedom rank of #121; its 90% source-sensitivity interval is #34–#469. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #7 of 272); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #129 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Release source ↗repository created at proxy
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 | #199 / 272 | ↑12.66 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #265 / 272 | ↑47.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #196 / 272 | ↑54.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #136 / 270 | ↑96.36 | Source ↗official | |
| TACbase_welfare_rate | #47 / 94 | ↑27.56 | Source ↗self run |
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 | #7 / 272 | ↓47.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #73 / 272 | ↓54.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #129 / 270 | ↓96.36 | Source ↗official |