← Models

Model profile

Yalm

yandexdeveloper
2022-06-23release date
Not rankedSafety rank
#207 / 645Freedom rank

Evidence summary

Safety. Yalm 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, #39 of 40); its weakest is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #40 of 40).

Freedom. Yalm has an estimated Freedom rank of #207; its 90% source-sensitivity interval is #7–#608. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #1 of 40); its weakest is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #2 of 40).

Compare this model

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

Official and reference links

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-evalRankValueDistributionSource
HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction#39 / 400.02754Source ↗official
HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction#40 / 400.157Source ↗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-evalRankValueDistributionSource
HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction#2 / 400.02754Source ↗official
HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction#1 / 400.157Source ↗official