Model profile
Granite 3.0 8B Instruct
Evidence summary
Safety. Granite 3.0 8B 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 BlueBench AttaQ-100 (attaq_harmlessness_reward_pct, #3 of 18); its weakest is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #199 of 272).
Freedom. Granite 3.0 8B Instruct has an estimated Freedom rank of #478; its 90% source-sensitivity interval is #311–#551. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #127 of 272); its weakest is BlueBench AttaQ-100 (attaq_harmlessness_reward_pct, #16 of 18).
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 |
|---|---|---|---|---|
| BlueBench AttaQ-100attaq_harmlessness_reward_pct | #3 / 18 | ↑88.03 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #199 / 272 | ↑12.66 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #146 / 272 | ↑86.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #130 / 272 | ↑75 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #89 / 270 | ↑97.77 | 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 |
|---|---|---|---|---|
| BlueBench AttaQ-100attaq_harmlessness_reward_pct | #16 / 18 | ↓88.03 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #127 / 272 | ↓86.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #139 / 272 | ↓75 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #182 / 270 | ↓97.77 | Source ↗official |