Model profile
LFM2 700M
Evidence summary
Safety. LFM2 700M 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, #58 of 248); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #203 of 248).
Freedom. LFM2 700M has an estimated Freedom rank of #173; its 90% source-sensitivity interval is #61–#459. 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, #44 of 248); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #120 of 246).
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 | #58 / 248 | ↑26.36 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #203 / 248 | ↑79 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #163 / 248 | ↑55.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #127 / 246 | ↑96.21 | 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 | #44 / 248 | ↓79 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #81 / 248 | ↓55.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #120 / 246 | ↓96.21 | Source ↗official |