← Models

Model profile

Claude Mythos 5

1eval lineages

Evidence summary

Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is Gray Swan indirect prompt injection (15 attempts) (attack_success_probability_k15_pct, #2 of 13); its weakest is UK AISI active safety-research compromise continuation (active_compromise_continuation_rate_pct, #5 of 5).

Compare this model

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

Official and reference links

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
Gray Swan indirect prompt injection (15 attempts)attack_success_probability_k15_pct#2 / 132.6↓ lowerSource ↗official
UK AISI active safety-research compromise continuationactive_compromise_continuation_rate_pct#5 / 513.6↓ lowerSource ↗official