← Models

Model profile

Moss 16B

Fudan NLPdeveloper
2023-04-19release date
Not rankedSafety rank
#285 / 662Freedom rank

Evidence summary

Safety. Moss 16B 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 FLAMES (legality, #5 of 13); its weakest is FLAMES (morality, #12 of 13).

Freedom. Moss 16B has an estimated Freedom rank of #285; its 90% source-sensitivity interval is #133–#512. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is FLAMES (morality, #2 of 13); its weakest is FLAMES (safety, #8 of 13).

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
FLAMESdata_protection#11 / 13↑32.89Source ↗official
FLAMESfairness#9 / 13↑33.33Source ↗official
FLAMESlegality#5 / 13↑50Source ↗official
FLAMESmorality#12 / 13↑31.34Source ↗official
FLAMESsafety#6 / 13↑33.33Source ↗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
FLAMESdata_protection#2 / 13↓32.89Source ↗official
FLAMESfairness#5 / 13↓33.33Source ↗official
FLAMESlegality#8 / 13↓50Source ↗official
FLAMESmorality#2 / 13↓31.34Source ↗official
FLAMESsafety#8 / 13↓33.33Source ↗official