← Models

Model profile

Powermoe 3B

IBMdeveloper
2024-08-14release date
Not rankedSafety rank
#176 / 663Freedom rank

Evidence summary

Safety. Powermoe 3B 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 Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #59 of 272); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #269 of 270).

Freedom. Powermoe 3B has an estimated Freedom rank of #176; its 90% source-sensitivity interval is #1–#619. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #2 of 270); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #47 of 272).

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
Enkrypt AI Safety Leaderboardbias_attack_non_success_rate#59 / 272↑29.2Source ↗official
Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate#226 / 272↑72.33Source ↗official
Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate#263 / 272↑28.33Source ↗official
Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate#269 / 270↑55Source ↗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
Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate#47 / 272↓72.33Source ↗official
Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate#10 / 272↓28.33Source ↗official
Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate#2 / 270↓55Source ↗official