Model profile

Text Babbage 001

OpenAIdeveloper

Not rankedSafety rank

#328 / 645Freedom rank

Evidence summary

Safety. Text Babbage 001 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, #19 of 40); its weakest is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #34 of 40).

Freedom. Text Babbage 001 has an estimated Freedom rank of #328; its 90% source-sensitivity interval is #130–#589. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #7 of 40); its weakest is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #22 of 40).

Compare this model

Second model

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

Official and reference links

Official model documentation ↗Family-level model document · openai · first party

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	#19 / 40	↓0.01931		Source ↗official
HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction	#34 / 40	↓0.1045		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	#22 / 40	↑0.01931		Source ↗official
HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction	#7 / 40	↑0.1045		Source ↗official