Model profile
Granite 4.0 Small Guardian
Evidence summary
Safety. Granite 4.0 Small Guardian has an estimated Safety rank of #163; its 90% source-sensitivity interval is #12–#302. Its behavior-only rank is #168; company governance moves the combined estimate to #163. Published Safety evidence spans 6 eval lineages and 3 of 7 components. Its strongest relative result is HELM Safety (simple_safety_tests, #1 of 80); its weakest is HELM Safety (xstest, #78 of 80).
Freedom. Granite 4.0 Small Guardian has an estimated Freedom rank of #657; its 90% source-sensitivity interval is #412–#659. Published Freedom evidence spans 5 eval lineages and 1 of 1 components. Its strongest relative result is HELM Safety (harmbench, #56 of 80); its weakest is HELM Safety (xstest, #78 of 80).
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 ↗direct research preview identity date
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 |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #18 / 80 | ↑0.821 | Source ↗official | |
| HELM Safetyanthropic_red_team | #2 / 80 | ↑0.999 | Source ↗official | |
| HELM Safetybbq | #55 / 80 | ↑0.9 | Source ↗official | |
| HELM Safetyharmbench | #25 / 80 | ↑0.864 | Source ↗official | |
| HELM Safetysimple_safety_tests | #1 / 80 | ↑1 | Source ↗official | |
| HELM Safetyxstest | #78 / 80 | ↑0.806 | 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 |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #63 / 80 | ↓0.821 | Source ↗official | |
| HELM Safetyanthropic_red_team | #75 / 80 | ↓0.999 | Source ↗official | |
| HELM Safetyharmbench | #56 / 80 | ↓0.864 | Source ↗official | |
| HELM Safetysimple_safety_tests | #58 / 80 | ↓1 | Source ↗official | |
| HELM Safetyxstest | #78 / 80 | ↑0.806 | Source ↗official |