Model profile
Granite 3.3 8B Instruct
IBMdeveloper
2025-04-10release date
#212 / 267overall rank
8eval lineages
Evidence summary
Granite 3.3 8B Instruct has an estimated overall rank of #212; its 90% source-sensitivity interval is #29–#254. Its behavior-only rank is #216; company governance moves the combined estimate to #212. Published evidence spans 8 evals and 4 of 7 behavior components. Its strongest relative result is BlueBench AttaQ-100 (attaq_harmlessness_reward_pct, #1 of 18); its weakest is AA-Omniscience (hallucination_rate, #285 of 311).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗granite-3-3-8b-instruct
- Hugging Face ↗ibm-granite/granite-3.3-8b-instruct
- 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 | #285 / 311 | 0.9309 | ↓ lower | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #25 / 80 | 0.76 | ↑ higher | Source ↗official | |
| BlueBench AttaQ-100attaq_harmlessness_reward_pct | #1 / 18 | 88.44 | ↑ higher | Source ↗official | |
| HELM Safetyanthropic_red_team | #32 / 80 | 0.991 | ↑ higher | Source ↗official | |
| HELM Safetybbq | #65 / 80 | 0.84 | ↑ higher | Source ↗official | |
| HELM Safetyharmbench | #34 / 80 | 0.812 | ↑ higher | Source ↗official | |
| HELM Safetysimple_safety_tests | #54 / 80 | 0.975 | ↑ higher | Source ↗official | |
| HELM Safetyxstest | #68 / 80 | 0.907 | ↑ higher | Source ↗official |