Model profile
LFM2 350M
Evidence summary
Safety. LFM2 350M does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #106 of 272); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #234 of 272).
Freedom. LFM2 350M has an estimated Freedom rank of #114; its 90% source-sensitivity interval is #46–#457. 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, #39 of 272); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #159 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model page ↗Family-level model document · liquid ai · first party
- 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 | #106 / 272 | ↑19.38 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #234 / 272 | ↑69.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #226 / 272 | ↑43.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #111 / 270 | ↑97.12 | 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 | #39 / 272 | ↓69.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #44 / 272 | ↓43.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #159 / 270 | ↓97.12 | Source ↗official |