Model profile
Evidence summary
Safety. Bloom does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 4 of 7 components. Its strongest relative result is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #18 of 40); its weakest is SafetyPrompts (score, #13 of 15).
Freedom. Bloom has an estimated Freedom rank of #102; its 90% source-sensitivity interval is #75–#298. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is SafetyPrompts (score, #3 of 15); its weakest is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #23 of 40).
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
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 |
|---|---|---|---|---|
| HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction | #18 / 40 | ↓0.01905 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #28 / 40 | ↓0.09507 | Source ↗official | |
| SafetyPromptsscore | #13 / 15 | ↑41.65 | 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 |
|---|---|---|---|---|
| HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction | #23 / 40 | ↑0.01905 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #13 / 40 | ↑0.09507 | Source ↗official | |
| SafetyPromptsscore | #3 / 15 | ↓41.65 | Source ↗official |