← Models

Model profile

AquilaChat2 34B

baaideveloper
2023-10-11release date
Not rankedSafety rank
#480 / 645Freedom rank

Evidence summary

Safety. AquilaChat2 34B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is SuperCLUE Safety (traditional_safety, #3 of 31); its weakest is SuperCLUE Safety (responsible_ai, #18 of 31).

Freedom. AquilaChat2 34B has an estimated Freedom rank of #480; its 90% source-sensitivity interval is #276–#578. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SuperCLUE Safety (instruction_attack, #13 of 31); its weakest is SuperCLUE Safety (traditional_safety, #28 of 31).

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
SuperCLUE Safetyinstruction_attack#17 / 3162.07Source ↗official
SuperCLUE Safetyresponsible_ai#18 / 3154.55Source ↗official
SuperCLUE Safetytraditional_safety#3 / 3182.98Source ↗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
SuperCLUE Safetyinstruction_attack#13 / 3162.07Source ↗official
SuperCLUE Safetytraditional_safety#28 / 3182.98Source ↗official