← Models

Model profile

Command Xlarge Beta

1eval lineages

Evidence summary

Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #4 of 42); its weakest is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #8 of 42).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

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-evalRankValueDistributionBetterSource
HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction#8 / 420.003604↓ lowerSource ↗official
HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction#4 / 420.01614↓ lowerSource ↗official