Model profile
SeaLLM 7B v2
Evidence summary
Safety. SeaLLM 7B v2 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 (toxicity_attack_non_success_rate, #25 of 268); its weakest is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #220 of 270).
Freedom. SeaLLM 7B v2 has an estimated Freedom rank of #616; its 90% source-sensitivity interval is #463–#644. 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, #102 of 270); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #242 of 268).
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 | #220 / 270 | ↑11.63 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #110 / 270 | ↑88.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #166 / 270 | ↑61.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #25 / 268 | ↑99.45 | 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 | #158 / 270 | ↓88.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #102 / 270 | ↓61.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #242 / 268 | ↓99.45 | Source ↗official |