Model profile
Granite 4.0 H Small
2eval lineages
Evidence summary
Published evidence spans 2 evals and 4 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #21 of 258); its weakest is AA-Omniscience (hallucination_rate, #230 of 311).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗granite-4-0-h-small
- Official model page ↗Family-level model document · ibm · first party
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #230 / 311 | 0.8791 | ↓ lower | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #102 / 260 | 18.6 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #121 / 260 | 88.67 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #74 / 260 | 85.56 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #21 / 258 | 99.64 | ↑ higher | Source ↗official |