Model profile
Smollm 360M Instruct
Evidence summary
Safety. Smollm 360M Instruct 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, #4 of 270); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #260 of 270).
Freedom. Smollm 360M Instruct has an estimated Freedom rank of #219; its 90% source-sensitivity interval is #25–#636. 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, #11 of 270); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #138 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 | #4 / 270 | ↑76.23 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #130 / 270 | ↑87.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #260 / 270 | ↑28.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #228 / 268 | ↑90 | 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 | #138 / 270 | ↓87.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #11 / 270 | ↓28.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #41 / 268 | ↓90 | Source ↗official |