Model profile
Evidence summary
Safety. Xlarge does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #1 of 40); its weakest is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #8 of 40).
Freedom. Xlarge has an estimated Freedom rank of #614; its 90% source-sensitivity interval is #436–#641. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #33 of 40); its weakest is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #39 of 40).
Compare this model
Only models sharing at least one published sub-eval are listed.
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 | #1 / 40 | ↓0.002317 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #8 / 40 | ↓0.02018 | 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 | #39 / 40 | ↑0.002317 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #33 / 40 | ↑0.02018 | Source ↗official |