Model profile
Granite 3.0 1B A400M Instruct
Evidence summary
Safety. Granite 3.0 1B A400M 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 (harmful_attack_non_success_rate, #153 of 248); its weakest is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #236 of 248).
Freedom. Granite 3.0 1B A400M Instruct has an estimated Freedom rank of #128; its 90% source-sensitivity interval is #82–#373. 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, #75 of 248); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #96 of 248).
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 · ibm · 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 | #236 / 248 | ↑5.43 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #173 / 248 | ↑83.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #153 / 248 | ↑59.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #152 / 246 | ↑95.41 | 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 | #75 / 248 | ↓83.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #96 / 248 | ↓59.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #94 / 246 | ↓95.41 | Source ↗official |