Model profile
SmolLM2 360M Instruct
Evidence summary
Safety. SmolLM2 360M Instruct does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 3 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #43 of 248); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #230 of 248).
Freedom. SmolLM2 360M Instruct has an estimated Freedom rank of #171; its 90% source-sensitivity interval is #33–#529. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #18 of 248); its weakest is Open LLM Safety Index (strongreject_safety_rate, #18 of 21).
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 | #43 / 248 | ↑33.59 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #113 / 248 | ↑88.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #230 / 248 | ↑33.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #225 / 246 | ↑81.52 | Source ↗official | |
| Open LLM Safety Indexjailbreakbench_safety_rate | #7 / 21 | ↑0.4667 | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #4 / 21 | ↑0.8667 | 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 | #132 / 248 | ↓88.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #18 / 248 | ↓33.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #22 / 246 | ↓81.52 | Source ↗official | |
| Open LLM Safety Indexjailbreakbench_safety_rate | #13 / 21 | ↓0.4667 | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #18 / 21 | ↓0.8667 | Source ↗official |