Model profile
Bloom
2022-07-12release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 4 of 7 behavior components. Its strongest relative result is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #20 of 42); its weakest is SafetyPrompts (score, #13 of 15).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Model card ↗Exact model document · BigScience · 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 |
|---|---|---|---|---|---|
| HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction | #20 / 42 | 0.01905 | ↓ lower | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #30 / 42 | 0.09507 | ↓ lower | Source ↗official | |
| SafetyPromptsscore | #13 / 15 | 41.65 | ↑ higher | Source ↗official |