← Models

Model profile

Qwen2 57B A14B Instruct

1eval lineages

Evidence summary

Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #66 of 258); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #170 of 260).

Compare this model

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

Published eval results

Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionBetterSource
Enkrypt AI Safety Leaderboardbias_attack_non_success_rate#77 / 26022.22↑ higherSource ↗official
Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate#168 / 26086.33↑ higherSource ↗official
Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate#170 / 26055.56↑ higherSource ↗official
Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate#66 / 25898.32↑ higherSource ↗official