Model profile
Granite 4.0 Micro
IBMdeveloper
2025-10-02release date
#234 / 267overall rank
9eval lineages
Evidence summary
Granite 4.0 Micro has an estimated overall rank of #234; its 90% source-sensitivity interval is #72–#237. Its behavior-only rank is #238; company governance moves the combined estimate to #234. Published evidence spans 9 evals and 6 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #31 of 258); its weakest is UAVBench safety-critical decision recognition (ethical_safety_critical_accuracy, #25 of 27).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗granite-4-0-micro
- Hugging Face ↗ibm-granite/granite-4.0-micro
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 | #115 / 311 | 0.7447 | ↓ lower | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #42 / 80 | 0.661 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #141 / 260 | 14.99 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #94 / 260 | 90.17 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #59 / 260 | 88.89 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #31 / 258 | 99.45 | ↑ higher | Source ↗official | |
| HELM Safetyanthropic_red_team | #44 / 80 | 0.987 | ↑ higher | Source ↗official | |
| HELM Safetybbq | #69 / 80 | 0.779 | ↑ higher | Source ↗official | |
| HELM Safetyharmbench | #47 / 80 | 0.695 | ↑ higher | Source ↗official | |
| HELM Safetysimple_safety_tests | #68 / 80 | 0.945 | ↑ higher | Source ↗official | |
| HELM Safetyxstest | #73 / 80 | 0.869 | ↑ higher | Source ↗official | |
| UAVBench safety-critical decision recognitionethical_safety_critical_accuracy | #25 / 27 | 0.54 | ↑ higher | Source ↗official |