Model profile
Granite 3.2 2B Instruct
Evidence summary
Safety. Granite 3.2 2B 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 (toxicity_attack_non_success_rate, #9 of 268); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #190 of 270).
Freedom. Granite 3.2 2B Instruct has an estimated Freedom rank of #433; its 90% source-sensitivity interval is #207–#539. 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, #79 of 270); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #257 of 268).
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 | #9 / 18 | ↑84.87 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #180 / 270 | ↑13.18 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #130 / 270 | ↑87.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #190 / 270 | ↑55 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #9 / 268 | ↑99.82 | 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 | #10 / 18 | ↓84.87 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #138 / 270 | ↓87.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #79 / 270 | ↓55 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #257 / 268 | ↓99.82 | Source ↗official |